Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3789 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0784. Min Act: -0.1700
Data Index: 1637803 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0471. Min Act: -0.1700
Data Index: 5241089 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0784. Min Range: -4.0784
Max Act: 4.0471. Min Act: -0.1700
Data Index: 8772112 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9533. Min Act: -0.1700
Data Index: 7108050 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9533. Min Act: -0.1700
Data Index: 1938396 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9533. Min Act: -0.1700
Data Index: 8202038 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9533. Min Act: -0.1700
Data Index: 8058295 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9533. Min Act: -0.1700
Data Index: 6426062 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9533. Min Act: -0.1700
Data Index: 4809517 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9220. Min Act: -0.1700
Data Index: 1490936 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9533. Min Act: -0.1700
Data Index: 6583890 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9220. Min Act: -0.1700
Data Index: 3919463 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9220. Min Act: -0.1700
Data Index: 8042837 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9220. Min Act: -0.1700
Data Index: 5693043 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9220. Min Act: -0.1700
Data Index: 1315737 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9220. Min Act: -0.1700
Data Index: 8465364 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9220. Min Act: -0.1700
Data Index: 5395265 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.9220. Min Act: -0.1700
Data Index: 124998 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.8908. Min Act: -0.1700
Data Index: 1056012 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0784. Min Range: -4.0784
Max Act: 3.8908. Min Act: -0.1700
Data Index: 1088997 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19