Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4348. Min Range: -7.4348
Max Act: 7.4348. Min Act: -0.1700
Data Index: 673688 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4348. Min Range: -7.4348
Max Act: 7.2161. Min Act: -0.1700
Data Index: 6950172 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4348. Min Range: -7.4348
Max Act: 7.1536. Min Act: -0.1700
Data Index: 1924674 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4348. Min Range: -7.4348
Max Act: 7.0911. Min Act: -0.1700
Data Index: 3008458 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4348. Min Range: -7.4348
Max Act: 7.0598. Min Act: -0.1700
Data Index: 2157999 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4348. Min Range: -7.4348
Max Act: 7.0911. Min Act: -0.1700
Data Index: 7566929 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4348. Min Range: -7.4348
Max Act: 7.0598. Min Act: -0.1700
Data Index: 3353567 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4348. Min Range: -7.4348
Max Act: 7.0598. Min Act: -0.1700
Data Index: 6625261 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4348. Min Range: -7.4348
Max Act: 7.0286. Min Act: -0.1700
Data Index: 6016545 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9973. Min Act: -0.1700
Data Index: 654267 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9661. Min Act: -0.1700
Data Index: 8763574 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9661. Min Act: -0.1700
Data Index: 1464931 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9661. Min Act: -0.1699
Data Index: 2435023 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9973. Min Act: -0.1700
Data Index: 1968496 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9661. Min Act: -0.1700
Data Index: 377179 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9036. Min Act: -0.1700
Data Index: 2435026 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9348. Min Act: -0.1700
Data Index: 2065556 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9348. Min Act: -0.1700
Data Index: 6425024 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9036. Min Act: -0.1700
Data Index: 5679164 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4348. Min Range: -7.4348
Max Act: 6.9036. Min Act: -0.1700
Data Index: 2135626 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19