Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.6411. Min Act: -0.1700
Data Index: 6327175 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.6099. Min Act: -0.1700
Data Index: 1852863 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5786. Min Act: -0.1700
Data Index: 2457733 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.6099. Min Act: -0.1700
Data Index: 5129444 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5786. Min Act: -0.1700
Data Index: 3629717 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5786. Min Act: -0.1700
Data Index: 3766044 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5786. Min Act: -0.1700
Data Index: 1110590 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5474. Min Act: -0.1700
Data Index: 3766053 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5474. Min Act: -0.1700
Data Index: 1438319 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5474. Min Act: -0.1700
Data Index: 2544199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5474. Min Act: -0.1700
Data Index: 8776775 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5474. Min Act: -0.1700
Data Index: 8449223 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5474. Min Act: -0.1700
Data Index: 8332360 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5474. Min Act: -0.1700
Data Index: 6307691 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5161. Min Act: -0.1700
Data Index: 2214766 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5161. Min Act: -0.1700
Data Index: 3108723 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.4849. Min Act: -0.1700
Data Index: 3948352 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5161. Min Act: -0.1700
Data Index: 3194329 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5161. Min Act: -0.1700
Data Index: 4110231 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6411. Min Range: -4.6411
Max Act: 4.5161. Min Act: -0.1700
Data Index: 4980685 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19