Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2601 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.9890. Min Act: -0.1700
Data Index: 5657708 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.4890. Min Act: -0.1700
Data Index: 3826412 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.4265. Min Act: -0.1700
Data Index: 1306127 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.4265. Min Act: -0.1700
Data Index: 1875592 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.3953. Min Act: -0.1700
Data Index: 4873607 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.4578. Min Act: -0.1700
Data Index: 3554724 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.3015. Min Act: -0.1700
Data Index: 6611887 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.3328. Min Act: -0.1700
Data Index: 6799377 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.3640. Min Act: -0.1700
Data Index: 7806612 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.3015. Min Act: -0.1700
Data Index: 4218544 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.2703. Min Act: -0.1700
Data Index: 2537213 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.2703. Min Act: -0.1700
Data Index: 2699314 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.2703. Min Act: -0.1700
Data Index: 8428329 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.2703. Min Act: -0.1700
Data Index: 3682351 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.2078. Min Act: -0.1700
Data Index: 5084457 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.2078. Min Act: -0.1700
Data Index: 5657707 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.2078. Min Act: -0.1700
Data Index: 501464 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.2078. Min Act: -0.1700
Data Index: 7004822 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.1140. Min Act: -0.1700
Data Index: 7640559 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9890. Min Range: -7.9890
Max Act: 7.1140. Min Act: -0.1700
Data Index: 8070545 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19