Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3041 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.2962. Min Act: -0.1700
Data Index: 5431390 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.3275. Min Act: -0.1700
Data Index: 211925 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.2962. Min Act: -0.1700
Data Index: 3444190 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.2337. Min Act: -0.1700
Data Index: 8077105 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.2337. Min Act: -0.1700
Data Index: 8800818 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.2337. Min Act: -0.1700
Data Index: 5922166 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.2025. Min Act: -0.1700
Data Index: 1502392 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.2025. Min Act: -0.1700
Data Index: 501040 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.2025. Min Act: -0.1700
Data Index: 2459412 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.2025. Min Act: -0.1700
Data Index: 1798744 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.1712. Min Act: -0.1700
Data Index: 2039025 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.1399. Min Act: -0.1700
Data Index: 3297408 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.1712. Min Act: -0.1700
Data Index: 8726814 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.1399. Min Act: -0.1700
Data Index: 3836540 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.1399. Min Act: -0.1700
Data Index: 2800714 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.1087. Min Act: -0.1700
Data Index: 1035629 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.1087. Min Act: -0.1700
Data Index: 7081666 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.1087. Min Act: -0.1700
Data Index: 7006288 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.1087. Min Act: -0.1700
Data Index: 4989120 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3275. Min Range: -4.3275
Max Act: 4.1399. Min Act: -0.1700
Data Index: 6259734 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19