Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1819 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1047. Min Range: -4.1047
Max Act: 4.1047. Min Act: -0.1700
Data Index: 6794266 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.7295. Min Act: -0.1700
Data Index: 1335396 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.7139. Min Act: -0.1700
Data Index: 901689 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.6826. Min Act: -0.1700
Data Index: 5122263 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.6513. Min Act: -0.1700
Data Index: 7493698 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.6669. Min Act: -0.1700
Data Index: 7556432 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.6357. Min Act: -0.1700
Data Index: 3312150 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.6357. Min Act: -0.1700
Data Index: 7271247 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.6044. Min Act: -0.1700
Data Index: 374968 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.6200. Min Act: -0.1700
Data Index: 8335956 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.6044. Min Act: -0.1700
Data Index: 1862228 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.6200. Min Act: -0.1700
Data Index: 8179641 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.5731. Min Act: -0.1700
Data Index: 6062557 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.5887. Min Act: -0.1700
Data Index: 809171 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.5574. Min Act: -0.1700
Data Index: 2223301 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.5574. Min Act: -0.1700
Data Index: 5595665 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.5417. Min Act: -0.1700
Data Index: 4023149 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.5417. Min Act: -0.1700
Data Index: 2796278 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.5261. Min Act: -0.1700
Data Index: 7275402 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1047. Min Range: -4.1047
Max Act: 3.5417. Min Act: -0.1700
Data Index: 1121300 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19