Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 338 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.4881. Min Act: -0.1700
Data Index: 8098987 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.3319. Min Act: -0.1700
Data Index: 1806239 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.2694. Min Act: -0.1700
Data Index: 7512309 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.2381. Min Act: -0.1700
Data Index: 3049913 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.1756. Min Act: -0.1700
Data Index: 8622298 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.1756. Min Act: -0.1700
Data Index: 6962743 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.1756. Min Act: -0.1700
Data Index: 2947546 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.1444. Min Act: -0.1700
Data Index: 56590 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.0819. Min Act: -0.1700
Data Index: 4242439 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.0506. Min Act: -0.1700
Data Index: 3727561 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4881. Min Range: -6.4881
Max Act: 6.0194. Min Act: -0.1700
Data Index: 4256480 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4881. Min Range: -6.4881
Max Act: 5.9881. Min Act: -0.1700
Data Index: 5388743 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4881. Min Range: -6.4881
Max Act: 5.9881. Min Act: -0.1700
Data Index: 6266849 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4881. Min Range: -6.4881
Max Act: 5.9881. Min Act: -0.1700
Data Index: 292408 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4881. Min Range: -6.4881
Max Act: 5.9256. Min Act: -0.1700
Data Index: 7296901 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4881. Min Range: -6.4881
Max Act: 5.9256. Min Act: -0.1700
Data Index: 3548204 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4881. Min Range: -6.4881
Max Act: 5.9256. Min Act: -0.1700
Data Index: 8711081 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4881. Min Range: -6.4881
Max Act: 5.9256. Min Act: -0.1700
Data Index: 6370218 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4881. Min Range: -6.4881
Max Act: 5.8631. Min Act: -0.1700
Data Index: 56591 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4881. Min Range: -6.4881
Max Act: 5.8944. Min Act: -0.1700
Data Index: 3740269 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19