Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.7092. Min Act: -0.1700
Data Index: 8074639 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.5842. Min Act: -0.1700
Data Index: 2196631 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.4592. Min Act: -0.1700
Data Index: 5182573 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.3967. Min Act: -0.1700
Data Index: 7092827 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.3342. Min Act: -0.1700
Data Index: 2904270 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.1467. Min Act: -0.1700
Data Index: 3344240 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.1467. Min Act: -0.1700
Data Index: 242717 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.0842. Min Act: -0.1700
Data Index: 8632527 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.0217. Min Act: -0.1700
Data Index: 8406834 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.0217. Min Act: -0.1700
Data Index: 8419644 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.0217. Min Act: -0.1700
Data Index: 5612119 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7092. Min Range: -9.7092
Max Act: 9.0217. Min Act: -0.1700
Data Index: 6258386 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7092. Min Range: -9.7092
Max Act: 8.9592. Min Act: -0.1700
Data Index: 3785537 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7092. Min Range: -9.7092
Max Act: 8.9592. Min Act: -0.1700
Data Index: 4855754 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7092. Min Range: -9.7092
Max Act: 8.9592. Min Act: -0.1700
Data Index: 8341893 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7092. Min Range: -9.7092
Max Act: 8.9592. Min Act: -0.1700
Data Index: 1191761 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7092. Min Range: -9.7092
Max Act: 8.9592. Min Act: -0.1700
Data Index: 5356613 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7092. Min Range: -9.7092
Max Act: 8.8967. Min Act: -0.1700
Data Index: 4559052 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7092. Min Range: -9.7092
Max Act: 8.8967. Min Act: -0.1700
Data Index: 1831312 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7092. Min Range: -9.7092
Max Act: 8.8967. Min Act: -0.1700
Data Index: 1540000 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19