Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3660 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.7557. Min Act: -0.1700
Data Index: 287336 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.7244. Min Act: -0.1700
Data Index: 5878428 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.5369. Min Act: -0.1700
Data Index: 1139641 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.5681. Min Act: -0.1700
Data Index: 482440 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.5681. Min Act: -0.1700
Data Index: 8681170 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.5056. Min Act: -0.1700
Data Index: 4988225 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.4744. Min Act: -0.1700
Data Index: 6174165 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.4119. Min Act: -0.1700
Data Index: 6630015 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.4119. Min Act: -0.1700
Data Index: 8204367 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.4119. Min Act: -0.1700
Data Index: 1474801 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.4119. Min Act: -0.1700
Data Index: 6900733 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.4119. Min Act: -0.1700
Data Index: 4754684 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.4119. Min Act: -0.1700
Data Index: 5752580 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.4119. Min Act: -0.1700
Data Index: 4209320 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.3806. Min Act: -0.1700
Data Index: 3732550 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.3806. Min Act: -0.1700
Data Index: 8567344 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.3806. Min Act: -0.1700
Data Index: 2087187 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.3806. Min Act: -0.1700
Data Index: 7907472 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.3806. Min Act: -0.1700
Data Index: 5821307 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7557. Min Range: -4.7557
Max Act: 4.3806. Min Act: -0.1700
Data Index: 2087189 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19