Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2327 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.7244. Min Act: -0.1700
Data Index: 983186 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5994. Min Act: -0.1700
Data Index: 1557707 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5681. Min Act: -0.1700
Data Index: 8530978 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5681. Min Act: -0.1700
Data Index: 8375780 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5681. Min Act: -0.1700
Data Index: 5559632 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5681. Min Act: -0.1700
Data Index: 5559633 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5369. Min Act: -0.1700
Data Index: 7353463 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5369. Min Act: -0.1700
Data Index: 6789099 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5056. Min Act: -0.1700
Data Index: 5054349 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5056. Min Act: -0.1700
Data Index: 2974352 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4431. Min Act: -0.1700
Data Index: 8045165 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.5056. Min Act: -0.1700
Data Index: 370947 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4744. Min Act: -0.1700
Data Index: 7158819 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4744. Min Act: -0.1700
Data Index: 4384050 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4431. Min Act: -0.1700
Data Index: 8375777 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4431. Min Act: -0.1700
Data Index: 8045161 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4119. Min Act: -0.1700
Data Index: 3939178 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4119. Min Act: -0.1700
Data Index: 6194125 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.4119. Min Act: -0.1700
Data Index: 361596 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7244. Min Range: -6.7244
Max Act: 6.3806. Min Act: -0.1700
Data Index: 361599 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19