Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3527 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.3397. Min Act: -0.1700
Data Index: 8438481 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.3085. Min Act: -0.1700
Data Index: 2313914 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.2772. Min Act: -0.1700
Data Index: 7977691 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.2460. Min Act: -0.1700
Data Index: 4667115 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.2147. Min Act: -0.1700
Data Index: 938611 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.1835. Min Act: -0.1700
Data Index: 897197 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.1522. Min Act: -0.1700
Data Index: 3813186 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.1210. Min Act: -0.1700
Data Index: 8693773 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.1210. Min Act: -0.1700
Data Index: 5685390 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0585. Min Act: -0.1700
Data Index: 5163993 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0585. Min Act: -0.1700
Data Index: 2487433 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3397. Min Range: -6.3397
Max Act: 6.0585. Min Act: -0.1700
Data Index: 5033625 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3397. Min Range: -6.3397
Max Act: 5.9960. Min Act: -0.1700
Data Index: 2633287 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3397. Min Range: -6.3397
Max Act: 5.9960. Min Act: -0.1700
Data Index: 6841058 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3397. Min Range: -6.3397
Max Act: 5.9335. Min Act: -0.1700
Data Index: 1957196 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3397. Min Range: -6.3397
Max Act: 5.9335. Min Act: -0.1700
Data Index: 5943199 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3397. Min Range: -6.3397
Max Act: 5.9335. Min Act: -0.1700
Data Index: 7616109 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3397. Min Range: -6.3397
Max Act: 5.9335. Min Act: -0.1700
Data Index: 1665097 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3397. Min Range: -6.3397
Max Act: 5.9022. Min Act: -0.1700
Data Index: 8227269 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3397. Min Range: -6.3397
Max Act: 5.9022. Min Act: -0.1700
Data Index: 6761921 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19