Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1216 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4925. Min Range: -6.4925
Max Act: 6.4925. Min Act: -0.1700
Data Index: 3056561 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4925. Min Range: -6.4925
Max Act: 6.3988. Min Act: -0.1700
Data Index: 3989699 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4925. Min Range: -6.4925
Max Act: 6.3675. Min Act: -0.1700
Data Index: 7881431 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4925. Min Range: -6.4925
Max Act: 6.2425. Min Act: -0.1700
Data Index: 6086446 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4925. Min Range: -6.4925
Max Act: 6.0863. Min Act: -0.1700
Data Index: 6032175 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.9925. Min Act: -0.1700
Data Index: 1780398 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.9300. Min Act: -0.1700
Data Index: 3009705 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.8988. Min Act: -0.1700
Data Index: 3526417 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.8988. Min Act: -0.1700
Data Index: 5018228 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.8988. Min Act: -0.1700
Data Index: 6915429 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.8675. Min Act: -0.1700
Data Index: 907658 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.8363. Min Act: -0.1700
Data Index: 981666 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.8363. Min Act: -0.1700
Data Index: 8729064 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.8675. Min Act: -0.1700
Data Index: 578300 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.8050. Min Act: -0.1700
Data Index: 4465151 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.8050. Min Act: -0.1700
Data Index: 7900953 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.8050. Min Act: -0.1700
Data Index: 6734006 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.7738. Min Act: -0.1700
Data Index: 3293568 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.7738. Min Act: -0.1700
Data Index: 5939624 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4925. Min Range: -6.4925
Max Act: 5.7738. Min Act: -0.1700
Data Index: 3841042 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19