Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 416 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4557. Min Range: -7.4557
Max Act: 7.4557. Min Act: -0.1700
Data Index: 643451 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4557. Min Range: -7.4557
Max Act: 7.1120. Min Act: -0.1700
Data Index: 7849394 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4557. Min Range: -7.4557
Max Act: 7.0807. Min Act: -0.1700
Data Index: 4973579 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.9870. Min Act: -0.1700
Data Index: 8686695 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.8932. Min Act: -0.1700
Data Index: 2287872 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.8932. Min Act: -0.1700
Data Index: 5770273 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.8932. Min Act: -0.1700
Data Index: 1269069 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.8932. Min Act: -0.1700
Data Index: 2390171 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.8307. Min Act: -0.1700
Data Index: 8333946 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.8307. Min Act: -0.1700
Data Index: 712524 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.8307. Min Act: -0.1700
Data Index: 6508331 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.7995. Min Act: -0.1700
Data Index: 7146098 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.7682. Min Act: -0.1700
Data Index: 1201942 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.7370. Min Act: -0.1700
Data Index: 8812262 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.7370. Min Act: -0.1700
Data Index: 4116114 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.7057. Min Act: -0.1700
Data Index: 4862822 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.7370. Min Act: -0.1700
Data Index: 3570641 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.7370. Min Act: -0.1700
Data Index: 1690961 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.7370. Min Act: -0.1700
Data Index: 1364077 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4557. Min Range: -7.4557
Max Act: 6.7057. Min Act: -0.1700
Data Index: 6346959 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19