Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 194 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0992. Min Range: -7.0992
Max Act: 7.0992. Min Act: -0.1700
Data Index: 2742552 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.9117. Min Act: -0.1700
Data Index: 6158900 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.8492. Min Act: -0.1700
Data Index: 6882620 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.7242. Min Act: -0.1700
Data Index: 4605589 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.7554. Min Act: -0.1700
Data Index: 4674403 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.7554. Min Act: -0.1700
Data Index: 5253892 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.7242. Min Act: -0.1700
Data Index: 4215862 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.7242. Min Act: -0.1700
Data Index: 8100942 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6929. Min Act: -0.1700
Data Index: 524615 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6929. Min Act: -0.1700
Data Index: 3276911 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6929. Min Act: -0.1700
Data Index: 3450502 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6929. Min Act: -0.1700
Data Index: 7953147 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6617. Min Act: -0.1700
Data Index: 1841052 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6617. Min Act: -0.1700
Data Index: 3970282 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6617. Min Act: -0.1700
Data Index: 4697375 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6617. Min Act: -0.1700
Data Index: 2921629 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6617. Min Act: -0.1700
Data Index: 1186911 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6617. Min Act: -0.1700
Data Index: 4340830 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6304. Min Act: -0.1700
Data Index: 4759332 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0992. Min Range: -7.0992
Max Act: 6.6304. Min Act: -0.1700
Data Index: 4259738 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19