Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0161. Min Range: -12.0161
Max Act: 12.0161. Min Act: -0.1700
Data Index: 3527788 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.7661. Min Act: -0.1700
Data Index: 6948219 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.6411. Min Act: -0.1700
Data Index: 7839464 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.3286. Min Act: -0.1700
Data Index: 7450232 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.2661. Min Act: -0.1700
Data Index: 5895827 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.2661. Min Act: -0.1700
Data Index: 1955824 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.2036. Min Act: -0.1700
Data Index: 7962590 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.2036. Min Act: -0.1700
Data Index: 5256715 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.2036. Min Act: -0.1700
Data Index: 72585 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.1411. Min Act: -0.1700
Data Index: 5933883 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.0786. Min Act: -0.1700
Data Index: 1099091 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.0786. Min Act: -0.1700
Data Index: 7372216 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.0786. Min Act: -0.1700
Data Index: 8013233 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.0161. Min Act: -0.1700
Data Index: 200854 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0161. Min Range: -12.0161
Max Act: 11.0161. Min Act: -0.1700
Data Index: 6781280 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0161. Min Range: -12.0161
Max Act: 10.9536. Min Act: -0.1700
Data Index: 1668009 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0161. Min Range: -12.0161
Max Act: 10.8911. Min Act: -0.1700
Data Index: 6849586 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0161. Min Range: -12.0161
Max Act: 10.8911. Min Act: -0.1700
Data Index: 7806180 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0161. Min Range: -12.0161
Max Act: 10.8911. Min Act: -0.1700
Data Index: 6781290 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0161. Min Range: -12.0161
Max Act: 10.8286. Min Act: -0.1700
Data Index: 5912732 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19