Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2355 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.7714. Min Act: -0.1700
Data Index: 8643782 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.7089. Min Act: -0.1700
Data Index: 1942447 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.7089. Min Act: -0.1700
Data Index: 4163539 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.6464. Min Act: -0.1700
Data Index: 608785 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.6152. Min Act: -0.1700
Data Index: 812845 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.6152. Min Act: -0.1700
Data Index: 6207850 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.6464. Min Act: -0.1700
Data Index: 6978476 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.5214. Min Act: -0.1700
Data Index: 1652990 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.4902. Min Act: -0.1700
Data Index: 7358382 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.4589. Min Act: -0.1700
Data Index: 4336446 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.4589. Min Act: -0.1700
Data Index: 1283637 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.4589. Min Act: -0.1700
Data Index: 2919973 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.4277. Min Act: -0.1700
Data Index: 1359974 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.3964. Min Act: -0.1700
Data Index: 1304315 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.3964. Min Act: -0.1700
Data Index: 568315 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.4277. Min Act: -0.1700
Data Index: 6170855 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.3652. Min Act: -0.1700
Data Index: 6503834 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.3652. Min Act: -0.1700
Data Index: 2656755 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.3339. Min Act: -0.1700
Data Index: 5905097 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7714. Min Range: -5.7714
Max Act: 5.3339. Min Act: -0.1700
Data Index: 4297975 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19