Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.8381. Min Act: -0.1700
Data Index: 4172405 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.7443. Min Act: -0.1700
Data Index: 1846693 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.5881. Min Act: -0.1700
Data Index: 8365329 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.2443. Min Act: -0.1700
Data Index: 523003 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.2131. Min Act: -0.1700
Data Index: 2111397 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.1506. Min Act: -0.1700
Data Index: 3946231 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.1193. Min Act: -0.1700
Data Index: 5293672 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.1506. Min Act: -0.1700
Data Index: 6861746 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.0881. Min Act: -0.1700
Data Index: 4586626 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.0881. Min Act: -0.1700
Data Index: 8128349 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8381. Min Range: -6.8381
Max Act: 5.9943. Min Act: -0.1700
Data Index: 3109536 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8381. Min Range: -6.8381
Max Act: 5.9943. Min Act: -0.1700
Data Index: 6079044 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8381. Min Range: -6.8381
Max Act: 5.9631. Min Act: -0.1700
Data Index: 2394457 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8381. Min Range: -6.8381
Max Act: 5.9631. Min Act: -0.1700
Data Index: 7106720 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8381. Min Range: -6.8381
Max Act: 5.9318. Min Act: -0.1700
Data Index: 5964179 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8381. Min Range: -6.8381
Max Act: 5.9318. Min Act: -0.1700
Data Index: 2801565 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8381. Min Range: -6.8381
Max Act: 5.9006. Min Act: -0.1700
Data Index: 5184378 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8381. Min Range: -6.8381
Max Act: 5.9006. Min Act: -0.1700
Data Index: 2990560 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8381. Min Range: -6.8381
Max Act: 5.8381. Min Act: -0.1700
Data Index: 910363 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8381. Min Range: -6.8381
Max Act: 5.8381. Min Act: -0.1700
Data Index: 946586 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19