Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2940 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6932. Min Range: -6.6932
Max Act: 6.6932. Min Act: -0.1700
Data Index: 1114064 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6932. Min Range: -6.6932
Max Act: 6.4432. Min Act: -0.1700
Data Index: 758523 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6932. Min Range: -6.6932
Max Act: 6.1307. Min Act: -0.1700
Data Index: 2590449 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6932. Min Range: -6.6932
Max Act: 6.0057. Min Act: -0.1700
Data Index: 6845367 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.9432. Min Act: -0.1700
Data Index: 6305743 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.9432. Min Act: -0.1700
Data Index: 7001207 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.9120. Min Act: -0.1700
Data Index: 4914574 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.9120. Min Act: -0.1700
Data Index: 2878428 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.9120. Min Act: -0.1700
Data Index: 2577990 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.9120. Min Act: -0.1700
Data Index: 6333438 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.8495. Min Act: -0.1700
Data Index: 4420799 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.8495. Min Act: -0.1700
Data Index: 772471 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.8182. Min Act: -0.1700
Data Index: 2708684 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.8495. Min Act: -0.1700
Data Index: 6639283 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.8807. Min Act: -0.1700
Data Index: 1083142 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.8495. Min Act: -0.1700
Data Index: 4411292 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.8807. Min Act: -0.1700
Data Index: 3759546 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.8182. Min Act: -0.1700
Data Index: 1205824 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.7870. Min Act: -0.1700
Data Index: 5644167 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6932. Min Range: -6.6932
Max Act: 5.7870. Min Act: -0.1700
Data Index: 7600867 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19