Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.5315. Min Act: -0.1700
Data Index: 2049142 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.5315. Min Act: -0.1700
Data Index: 8681235 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.4065. Min Act: -0.1700
Data Index: 2049141 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.3440. Min Act: -0.1700
Data Index: 5790333 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.2815. Min Act: -0.1700
Data Index: 873231 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.0940. Min Act: -0.1700
Data Index: 3735019 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.0315. Min Act: -0.1700
Data Index: 1520165 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.0315. Min Act: -0.1700
Data Index: 5215387 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.0315. Min Act: -0.1700
Data Index: 4158520 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.0315. Min Act: -0.1700
Data Index: 5693280 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5315. Min Range: -8.5315
Max Act: 8.0315. Min Act: -0.1700
Data Index: 6859042 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5315. Min Range: -8.5315
Max Act: 7.9690. Min Act: -0.1700
Data Index: 8792947 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5315. Min Range: -8.5315
Max Act: 7.9065. Min Act: -0.1700
Data Index: 6350414 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5315. Min Range: -8.5315
Max Act: 7.9690. Min Act: -0.1700
Data Index: 1539036 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5315. Min Range: -8.5315
Max Act: 7.9065. Min Act: -0.1700
Data Index: 25071 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5315. Min Range: -8.5315
Max Act: 7.9065. Min Act: -0.1700
Data Index: 1786874 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5315. Min Range: -8.5315
Max Act: 7.9065. Min Act: -0.1700
Data Index: 8164110 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5315. Min Range: -8.5315
Max Act: 7.9065. Min Act: -0.1700
Data Index: 8118639 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5315. Min Range: -8.5315
Max Act: 7.9065. Min Act: -0.1700
Data Index: 4351288 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5315. Min Range: -8.5315
Max Act: 7.9065. Min Act: -0.1700
Data Index: 964891 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19