Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2792. Min Range: -6.2792
Max Act: 6.2792. Min Act: -0.1700
Data Index: 982268 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2792. Min Range: -6.2792
Max Act: 6.2792. Min Act: -0.1700
Data Index: 5805556 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2792. Min Range: -6.2792
Max Act: 6.2479. Min Act: -0.1700
Data Index: 1631503 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2792. Min Range: -6.2792
Max Act: 6.2167. Min Act: -0.1700
Data Index: 1642320 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2792. Min Range: -6.2792
Max Act: 6.1854. Min Act: -0.1700
Data Index: 4947209 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2792. Min Range: -6.2792
Max Act: 6.1229. Min Act: -0.1700
Data Index: 7494509 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2792. Min Range: -6.2792
Max Act: 6.1229. Min Act: -0.1700
Data Index: 7494510 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.9667. Min Act: -0.1700
Data Index: 4897166 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.9979. Min Act: -0.1700
Data Index: 888905 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.9667. Min Act: -0.1700
Data Index: 6670355 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.9042. Min Act: -0.1700
Data Index: 2660556 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.8417. Min Act: -0.1700
Data Index: 427777 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.8104. Min Act: -0.1700
Data Index: 4831082 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.8104. Min Act: -0.1700
Data Index: 4053309 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.8104. Min Act: -0.1700
Data Index: 6606627 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.7167. Min Act: -0.1700
Data Index: 888906 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.6854. Min Act: -0.1700
Data Index: 2182047 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.6542. Min Act: -0.1700
Data Index: 3559126 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.6542. Min Act: -0.1700
Data Index: 8123898 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2792. Min Range: -6.2792
Max Act: 5.6542. Min Act: -0.1700
Data Index: 4920200 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19