Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4585 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.6084. Min Act: -0.1700
Data Index: 7807599 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.5771. Min Act: -0.1700
Data Index: 5402231 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.5771. Min Act: -0.1700
Data Index: 2538233 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.5146. Min Act: -0.1700
Data Index: 8192025 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.4521. Min Act: -0.1700
Data Index: 6475452 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.4521. Min Act: -0.1700
Data Index: 5402232 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.4209. Min Act: -0.1700
Data Index: 76328 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.4209. Min Act: -0.1700
Data Index: 2855407 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.3896. Min Act: -0.1700
Data Index: 7579766 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.3584. Min Act: -0.1700
Data Index: 6475450 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.3271. Min Act: -0.1700
Data Index: 1658130 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.2646. Min Act: -0.1700
Data Index: 2855408 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.2334. Min Act: -0.1700
Data Index: 2650101 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.2021. Min Act: -0.1700
Data Index: 6578049 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.2021. Min Act: -0.1700
Data Index: 6288811 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.2021. Min Act: -0.1700
Data Index: 1170061 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.2021. Min Act: -0.1700
Data Index: 7971995 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.2021. Min Act: -0.1700
Data Index: 1051843 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.2021. Min Act: -0.1700
Data Index: 7971277 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6084. Min Range: -5.6084
Max Act: 5.2334. Min Act: -0.1700
Data Index: 2525403 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19