Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.5101. Min Act: -0.1700
Data Index: 4841356 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.4163. Min Act: -0.1700
Data Index: 1989051 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.3851. Min Act: -0.1700
Data Index: 6447355 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.2601. Min Act: -0.1700
Data Index: 6281464 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.2288. Min Act: -0.1700
Data Index: 2933741 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.1976. Min Act: -0.1700
Data Index: 9610 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.1976. Min Act: -0.1700
Data Index: 2246761 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.1351. Min Act: -0.1700
Data Index: 2197574 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.1351. Min Act: -0.1700
Data Index: 6409021 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.1038. Min Act: -0.1700
Data Index: 7684505 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.0726. Min Act: -0.1700
Data Index: 2951823 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.0726. Min Act: -0.1700
Data Index: 4328730 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.0726. Min Act: -0.1700
Data Index: 4021785 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.0413. Min Act: -0.1700
Data Index: 7659115 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.0413. Min Act: -0.1700
Data Index: 3543967 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.0413. Min Act: -0.1700
Data Index: 1923632 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.0101. Min Act: -0.1700
Data Index: 1259127 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.0101. Min Act: -0.1700
Data Index: 6319558 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.0101. Min Act: -0.1700
Data Index: 5945573 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5101. Min Range: -7.5101
Max Act: 7.0101. Min Act: -0.1700
Data Index: 2231004 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19