Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6160 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.7959. Min Act: -0.1700
Data Index: 2318419 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.7959. Min Act: -0.1700
Data Index: 8773210 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.7959. Min Act: -0.1700
Data Index: 5518421 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.7021. Min Act: -0.1700
Data Index: 6925494 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.6084. Min Act: -0.1700
Data Index: 1802743 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.6084. Min Act: -0.1700
Data Index: 3469602 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.6084. Min Act: -0.1700
Data Index: 1317855 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.5146. Min Act: -0.1700
Data Index: 2142828 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.4834. Min Act: -0.1700
Data Index: 8547122 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.4834. Min Act: -0.1700
Data Index: 8672616 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.4521. Min Act: -0.1700
Data Index: 6281583 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.3896. Min Act: -0.1700
Data Index: 358424 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.3896. Min Act: -0.1700
Data Index: 5552619 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.3896. Min Act: -0.1700
Data Index: 3240862 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.3896. Min Act: -0.1700
Data Index: 4513398 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.3896. Min Act: -0.1700
Data Index: 8631854 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.3584. Min Act: -0.1700
Data Index: 370059 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.3584. Min Act: -0.1700
Data Index: 398178 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.3584. Min Act: -0.1700
Data Index: 2673642 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7959. Min Range: -4.7959
Max Act: 4.3271. Min Act: -0.1700
Data Index: 7563029 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19