Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1248 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1712. Min Range: -8.1712
Max Act: 8.1712. Min Act: -0.1700
Data Index: 8362192 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1712. Min Range: -8.1712
Max Act: 8.1087. Min Act: -0.1700
Data Index: 2535468 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1712. Min Range: -8.1712
Max Act: 8.1087. Min Act: -0.1700
Data Index: 5237833 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.8587. Min Act: -0.1700
Data Index: 3494210 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.8587. Min Act: -0.1700
Data Index: 8199809 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.7962. Min Act: -0.1700
Data Index: 194415 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.7962. Min Act: -0.1700
Data Index: 7009621 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.7962. Min Act: -0.1700
Data Index: 7582062 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.7962. Min Act: -0.1700
Data Index: 4735161 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.7337. Min Act: -0.1700
Data Index: 3029054 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.6399. Min Act: -0.1700
Data Index: 1716525 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.7024. Min Act: -0.1700
Data Index: 7217259 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.7024. Min Act: -0.1700
Data Index: 1274643 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.6399. Min Act: -0.1700
Data Index: 3296489 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.6399. Min Act: -0.1700
Data Index: 6843849 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.6087. Min Act: -0.1700
Data Index: 946609 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.6087. Min Act: -0.1700
Data Index: 1965964 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.6399. Min Act: -0.1700
Data Index: 4373783 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.6087. Min Act: -0.1700
Data Index: 833180 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1712. Min Range: -8.1712
Max Act: 7.6087. Min Act: -0.1700
Data Index: 6989803 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19