Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2076 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.3235. Min Act: -0.1700
Data Index: 7743099 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.3235. Min Act: -0.1700
Data Index: 7772752 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.2610. Min Act: -0.1700
Data Index: 7293269 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.3235. Min Act: -0.1700
Data Index: 4288764 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1985. Min Act: -0.1700
Data Index: 932405 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.2610. Min Act: -0.1700
Data Index: 1542642 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1985. Min Act: -0.1700
Data Index: 7439311 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1985. Min Act: -0.1700
Data Index: 2193 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1985. Min Act: -0.1700
Data Index: 694096 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1985. Min Act: -0.1700
Data Index: 7064150 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1985. Min Act: -0.1700
Data Index: 8127549 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1985. Min Act: -0.1700
Data Index: 8127550 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1360. Min Act: -0.1700
Data Index: 8272522 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1360. Min Act: -0.1700
Data Index: 249920 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1360. Min Act: -0.1700
Data Index: 4302580 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1360. Min Act: -0.1700
Data Index: 6692079 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1360. Min Act: -0.1700
Data Index: 7671077 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1360. Min Act: -0.1700
Data Index: 7455264 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.1360. Min Act: -0.1700
Data Index: 2494798 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3235. Min Range: -7.3235
Max Act: 7.0735. Min Act: -0.1700
Data Index: 1898013 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19