Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6130 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.3596. Min Act: -0.1700
Data Index: 6001904 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.3283. Min Act: -0.1700
Data Index: 941491 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2969. Min Act: -0.1700
Data Index: 6721285 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2969. Min Act: -0.1700
Data Index: 941505 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2340. Min Act: -0.1700
Data Index: 3404226 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2655. Min Act: -0.1700
Data Index: 941482 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2655. Min Act: -0.1700
Data Index: 4899873 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2655. Min Act: -0.1700
Data Index: 941485 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2340. Min Act: -0.1700
Data Index: 6421136 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2340. Min Act: -0.1700
Data Index: 290614 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2340. Min Act: -0.1700
Data Index: 941483 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2340. Min Act: -0.1700
Data Index: 6421153 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2026. Min Act: -0.1700
Data Index: 6920808 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2026. Min Act: -0.1700
Data Index: 941484 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2026. Min Act: -0.1700
Data Index: 2291009 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.2026. Min Act: -0.1700
Data Index: 4175191 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.1711. Min Act: -0.1700
Data Index: 941495 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.1711. Min Act: -0.1700
Data Index: 941504 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.1396. Min Act: -0.1700
Data Index: 941492 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3596. Min Range: -3.3596
Max Act: 3.1081. Min Act: -0.1700
Data Index: 941488 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19