Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2587 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.2593. Min Act: -0.1700
Data Index: 1654140 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.2435. Min Act: -0.1700
Data Index: 350973 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.2435. Min Act: -0.1700
Data Index: 8277279 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1807. Min Act: -0.1700
Data Index: 2570802 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1649. Min Act: -0.1700
Data Index: 2757838 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1649. Min Act: -0.1700
Data Index: 1652504 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1492. Min Act: -0.1700
Data Index: 2837547 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1492. Min Act: -0.1700
Data Index: 7723098 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1492. Min Act: -0.1700
Data Index: 588696 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1492. Min Act: -0.1700
Data Index: 5994956 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1492. Min Act: -0.1700
Data Index: 923620 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1334. Min Act: -0.1700
Data Index: 6217940 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1334. Min Act: -0.1700
Data Index: 1296915 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1334. Min Act: -0.1700
Data Index: 7092781 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1177. Min Act: -0.1700
Data Index: 1057651 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1177. Min Act: -0.1700
Data Index: 2062028 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1177. Min Act: -0.1700
Data Index: 6305467 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1177. Min Act: -0.1700
Data Index: 1318766 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1177. Min Act: -0.1700
Data Index: 644606 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1177. Min Act: -0.1700
Data Index: 7092782 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19