Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1027 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1240. Min Range: -7.1240
Max Act: 7.1240. Min Act: -0.1700
Data Index: 597543 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1240. Min Range: -7.1240
Max Act: 7.0303. Min Act: -0.1700
Data Index: 6546718 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.9990. Min Act: -0.1700
Data Index: 1268562 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.9678. Min Act: -0.1700
Data Index: 374999 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.9365. Min Act: -0.1700
Data Index: 983394 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.9053. Min Act: -0.1700
Data Index: 8617570 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.9053. Min Act: -0.1700
Data Index: 7929439 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8740. Min Act: -0.1700
Data Index: 6703733 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8740. Min Act: -0.1700
Data Index: 6269086 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8740. Min Act: -0.1700
Data Index: 7145348 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8740. Min Act: -0.1700
Data Index: 4380225 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8740. Min Act: -0.1700
Data Index: 4569875 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8740. Min Act: -0.1700
Data Index: 5207970 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8740. Min Act: -0.1700
Data Index: 6600899 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8740. Min Act: -0.1700
Data Index: 4846074 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8428. Min Act: -0.1700
Data Index: 4095756 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8428. Min Act: -0.1700
Data Index: 6042088 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8428. Min Act: -0.1700
Data Index: 6609655 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8428. Min Act: -0.1700
Data Index: 4314085 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1240. Min Range: -7.1240
Max Act: 6.8428. Min Act: -0.1700
Data Index: 6048692 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19