Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 828 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7425. Min Act: -0.1700
Data Index: 5817640 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7737. Min Act: -0.1700
Data Index: 5635914 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7112. Min Act: -0.1700
Data Index: 5485810 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7425. Min Act: -0.1700
Data Index: 3705396 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7425. Min Act: -0.1700
Data Index: 1903485 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7112. Min Act: -0.1700
Data Index: 2146332 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7112. Min Act: -0.1700
Data Index: 4975170 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7425. Min Act: -0.1700
Data Index: 4687148 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7112. Min Act: -0.1700
Data Index: 8753183 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7425. Min Act: -0.1700
Data Index: 7571205 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7112. Min Act: -0.1700
Data Index: 6895258 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.7112. Min Act: -0.1700
Data Index: 958742 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.6799. Min Act: -0.1700
Data Index: 5231415 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.6486. Min Act: -0.1700
Data Index: 8697004 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.6486. Min Act: -0.1700
Data Index: 3857053 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.6486. Min Act: -0.1700
Data Index: 6341902 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.6173. Min Act: -0.1700
Data Index: 4649771 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.6173. Min Act: -0.1700
Data Index: 2776364 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.6173. Min Act: -0.1700
Data Index: 4762764 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7737. Min Range: -3.7737
Max Act: 3.6173. Min Act: -0.1700
Data Index: 2846746 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19