Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3495 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.5019. Min Act: -0.1700
Data Index: 1622905 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.4844. Min Act: -0.1700
Data Index: 8271464 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.4492. Min Act: -0.1700
Data Index: 1009826 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.4668. Min Act: -0.1700
Data Index: 6244595 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.4492. Min Act: -0.1700
Data Index: 7338498 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 3954729 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.4316. Min Act: -0.1700
Data Index: 3620420 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.4140. Min Act: -0.1700
Data Index: 4977101 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.4140. Min Act: -0.1700
Data Index: 7901666 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 7913139 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 2171414 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 8548216 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 7628488 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 3260923 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 8767192 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 928293 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 70744 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.4140. Min Act: -0.1700
Data Index: 477438 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 1756217 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5019. Min Range: -1.5019
Max Act: 1.3964. Min Act: -0.1700
Data Index: 912912 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19