Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2913 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.6699. Min Act: -0.1700
Data Index: 6138692 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.6699. Min Act: -0.1700
Data Index: 6537758 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.6074. Min Act: -0.1700
Data Index: 8513739 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.6074. Min Act: -0.1700
Data Index: 6014046 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.5761. Min Act: -0.1700
Data Index: 7850061 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.5136. Min Act: -0.1700
Data Index: 7155537 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.3886. Min Act: -0.1700
Data Index: 2713660 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.3886. Min Act: -0.1700
Data Index: 7573567 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.3261. Min Act: -0.1700
Data Index: 2076734 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.3261. Min Act: -0.1700
Data Index: 2787640 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.3261. Min Act: -0.1700
Data Index: 1271054 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.2949. Min Act: -0.1700
Data Index: 7035168 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.2949. Min Act: -0.1700
Data Index: 2726183 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.2949. Min Act: -0.1700
Data Index: 8613351 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.2636. Min Act: -0.1700
Data Index: 6343195 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.2636. Min Act: -0.1700
Data Index: 4596943 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.2324. Min Act: -0.1700
Data Index: 2334599 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.2324. Min Act: -0.1700
Data Index: 1718300 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.2324. Min Act: -0.1700
Data Index: 3010094 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6699. Min Range: -5.6699
Max Act: 5.2324. Min Act: -0.1700
Data Index: 1814580 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19