Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6294 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1986. Min Range: -6.1986
Max Act: 6.1986. Min Act: -0.1700
Data Index: 6533118 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.8236. Min Act: -0.1700
Data Index: 4106783 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.5111. Min Act: -0.1700
Data Index: 598068 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.5111. Min Act: -0.1700
Data Index: 4367287 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.4799. Min Act: -0.1700
Data Index: 8412080 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.5111. Min Act: -0.1700
Data Index: 7262110 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.5111. Min Act: -0.1700
Data Index: 3846022 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.4799. Min Act: -0.1700
Data Index: 189394 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.4486. Min Act: -0.1700
Data Index: 2939584 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.3861. Min Act: -0.1700
Data Index: 1464314 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.3236. Min Act: -0.1700
Data Index: 4774351 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.3236. Min Act: -0.1700
Data Index: 7892969 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.2924. Min Act: -0.1700
Data Index: 8733774 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.2924. Min Act: -0.1700
Data Index: 7546695 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.3236. Min Act: -0.1700
Data Index: 2360923 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.2611. Min Act: -0.1700
Data Index: 3272163 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.2611. Min Act: -0.1700
Data Index: 7396247 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.2299. Min Act: -0.1700
Data Index: 485464 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.2299. Min Act: -0.1700
Data Index: 5658223 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1986. Min Range: -6.1986
Max Act: 5.2299. Min Act: -0.1700
Data Index: 7057720 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19