Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1152. Min Range: -6.1152
Max Act: 6.1152. Min Act: -0.1700
Data Index: 6526188 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1152. Min Range: -6.1152
Max Act: 6.0527. Min Act: -0.1700
Data Index: 294390 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.9902. Min Act: -0.1700
Data Index: 5563181 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.8964. Min Act: -0.1700
Data Index: 843875 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.8339. Min Act: -0.1700
Data Index: 2983880 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.8339. Min Act: -0.1700
Data Index: 2965728 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.8339. Min Act: -0.1700
Data Index: 5436359 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.8027. Min Act: -0.1700
Data Index: 4506942 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.7714. Min Act: -0.1700
Data Index: 6885826 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.7402. Min Act: -0.1700
Data Index: 2478022 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.7402. Min Act: -0.1700
Data Index: 265667 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.7402. Min Act: -0.1700
Data Index: 4020985 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.7089. Min Act: -0.1700
Data Index: 6524835 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.7089. Min Act: -0.1700
Data Index: 8672913 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.6777. Min Act: -0.1700
Data Index: 3623434 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.6777. Min Act: -0.1700
Data Index: 2822047 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.6777. Min Act: -0.1700
Data Index: 266675 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.6777. Min Act: -0.1700
Data Index: 1643447 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.6777. Min Act: -0.1700
Data Index: 4312775 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1152. Min Range: -6.1152
Max Act: 5.6777. Min Act: -0.1700
Data Index: 4864704 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19