Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1959 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4303. Min Range: -9.4303
Max Act: 9.4303. Min Act: -0.1700
Data Index: 3015322 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4303. Min Range: -9.4303
Max Act: 9.4303. Min Act: -0.1700
Data Index: 7522606 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4303. Min Range: -9.4303
Max Act: 9.1803. Min Act: -0.1700
Data Index: 354702 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4303. Min Range: -9.4303
Max Act: 9.1178. Min Act: -0.1700
Data Index: 695920 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4303. Min Range: -9.4303
Max Act: 9.0553. Min Act: -0.1700
Data Index: 6613358 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4303. Min Range: -9.4303
Max Act: 9.0553. Min Act: -0.1700
Data Index: 6559433 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4303. Min Range: -9.4303
Max Act: 9.0553. Min Act: -0.1700
Data Index: 8015143 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.9928. Min Act: -0.1700
Data Index: 5430100 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.9928. Min Act: -0.1700
Data Index: 6565018 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.9928. Min Act: -0.1700
Data Index: 3624818 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.9928. Min Act: -0.1700
Data Index: 6413022 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.9928. Min Act: -0.1700
Data Index: 6614743 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.9303. Min Act: -0.1700
Data Index: 7666815 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.8678. Min Act: -0.1700
Data Index: 892512 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.8678. Min Act: -0.1700
Data Index: 8228990 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.8678. Min Act: -0.1700
Data Index: 2062010 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.8678. Min Act: -0.1700
Data Index: 210208 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.8053. Min Act: -0.1700
Data Index: 2971622 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.8053. Min Act: -0.1700
Data Index: 3435554 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4303. Min Range: -9.4303
Max Act: 8.8053. Min Act: -0.1700
Data Index: 6094806 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19