Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5324 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.4668. Min Act: -0.1700
Data Index: 8203198 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.4668. Min Act: -0.1700
Data Index: 2716094 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.3418. Min Act: -0.1700
Data Index: 4888140 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.2793. Min Act: -0.1700
Data Index: 5966889 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.2480. Min Act: -0.1700
Data Index: 1455211 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.2480. Min Act: -0.1700
Data Index: 5966899 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.2168. Min Act: -0.1700
Data Index: 5155579 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.1543. Min Act: -0.1700
Data Index: 2909237 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.0918. Min Act: -0.1700
Data Index: 6044325 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.0293. Min Act: -0.1700
Data Index: 5204374 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.0605. Min Act: -0.1700
Data Index: 5370449 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.0605. Min Act: -0.1700
Data Index: 8740310 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4668. Min Range: -8.4668
Max Act: 7.9980. Min Act: -0.1700
Data Index: 7912847 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4668. Min Range: -8.4668
Max Act: 7.9980. Min Act: -0.1700
Data Index: 4896446 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4668. Min Range: -8.4668
Max Act: 7.9668. Min Act: -0.1700
Data Index: 8790298 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4668. Min Range: -8.4668
Max Act: 8.0293. Min Act: -0.1700
Data Index: 8384391 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4668. Min Range: -8.4668
Max Act: 7.9980. Min Act: -0.1700
Data Index: 4630149 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4668. Min Range: -8.4668
Max Act: 7.9355. Min Act: -0.1700
Data Index: 2158389 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4668. Min Range: -8.4668
Max Act: 7.9355. Min Act: -0.1700
Data Index: 8708813 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4668. Min Range: -8.4668
Max Act: 7.8730. Min Act: -0.1700
Data Index: 4670370 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19