Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2894 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.9149. Min Act: -0.1700
Data Index: 3963836 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.8212. Min Act: -0.1700
Data Index: 1279244 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.6962. Min Act: -0.1700
Data Index: 6736016 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.6962. Min Act: -0.1700
Data Index: 4542496 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.6649. Min Act: -0.1700
Data Index: 5218502 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.6649. Min Act: -0.1700
Data Index: 8828763 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.6337. Min Act: -0.1700
Data Index: 3835646 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.6337. Min Act: -0.1700
Data Index: 2089255 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.6337. Min Act: -0.1700
Data Index: 2737332 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.6024. Min Act: -0.1700
Data Index: 1203509 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.6024. Min Act: -0.1700
Data Index: 3385156 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.6024. Min Act: -0.1700
Data Index: 3227541 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.5712. Min Act: -0.1700
Data Index: 3735536 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.5712. Min Act: -0.1700
Data Index: 3342366 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.5712. Min Act: -0.1700
Data Index: 8270477 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.5712. Min Act: -0.1700
Data Index: 5799654 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.5399. Min Act: -0.1700
Data Index: 1398811 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.5399. Min Act: -0.1700
Data Index: 8795215 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.5399. Min Act: -0.1700
Data Index: 6020725 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9149. Min Range: -4.9149
Max Act: 4.5399. Min Act: -0.1700
Data Index: 5630439 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19