Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4766 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.4026. Min Act: -0.1698
Data Index: 3735603 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.4026. Min Act: -0.1591
Data Index: 7937195 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.4026. Min Act: -0.1674
Data Index: 319579 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.3401. Min Act: -0.1700
Data Index: 1912222 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.3401. Min Act: -0.1692
Data Index: 7902519 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.3401. Min Act: -0.1700
Data Index: 8076115 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.3401. Min Act: -0.1672
Data Index: 6129742 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.3401. Min Act: -0.1700
Data Index: 2914093 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2776. Min Act: -0.1682
Data Index: 4304604 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2151. Min Act: -0.1610
Data Index: 8630500 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2776. Min Act: -0.1698
Data Index: 3404840 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2151. Min Act: -0.1692
Data Index: 6295126 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2151. Min Act: -0.1681
Data Index: 5772318 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2151. Min Act: -0.1669
Data Index: 2961478 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2151. Min Act: -0.1696
Data Index: 5504457 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2151. Min Act: -0.1672
Data Index: 5473581 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2151. Min Act: -0.1698
Data Index: 5329653 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2151. Min Act: -0.1700
Data Index: 4913320 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2151. Min Act: -0.1692
Data Index: 4913321 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4026. Min Range: -10.4026
Max Act: 10.2151. Min Act: -0.1632
Data Index: 4673574 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19