Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5226 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2179. Min Range: -6.2179
Max Act: 6.2179. Min Act: -0.1700
Data Index: 3822800 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2179. Min Range: -6.2179
Max Act: 6.0929. Min Act: -0.1700
Data Index: 3414549 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.9991. Min Act: -0.1700
Data Index: 7701305 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.9679. Min Act: -0.1700
Data Index: 5315673 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.8741. Min Act: -0.1700
Data Index: 6254568 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.7804. Min Act: -0.1700
Data Index: 6026988 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.7804. Min Act: -0.1700
Data Index: 3720721 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.7179. Min Act: -0.1700
Data Index: 2280017 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.6866. Min Act: -0.1700
Data Index: 259194 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.6554. Min Act: -0.1700
Data Index: 2602254 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.6241. Min Act: -0.1698
Data Index: 6406054 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.6554. Min Act: -0.1700
Data Index: 1478848 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.6241. Min Act: -0.1699
Data Index: 4593586 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.6241. Min Act: -0.1700
Data Index: 5538536 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.5929. Min Act: -0.1700
Data Index: 2411457 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.5929. Min Act: -0.1700
Data Index: 8590859 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.6241. Min Act: -0.1700
Data Index: 6443082 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.6241. Min Act: -0.1700
Data Index: 5026524 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.6241. Min Act: -0.1700
Data Index: 6110090 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2179. Min Range: -6.2179
Max Act: 5.5616. Min Act: -0.1700
Data Index: 8484737 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19