Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4830 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.7348. Min Act: -0.1700
Data Index: 1588187 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4536. Min Act: -0.1700
Data Index: 2394037 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4536. Min Act: -0.1700
Data Index: 2733407 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4223. Min Act: -0.1700
Data Index: 5976468 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3911. Min Act: -0.1700
Data Index: 6219494 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3911. Min Act: -0.1700
Data Index: 3125766 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.4223. Min Act: -0.1700
Data Index: 1113201 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3911. Min Act: -0.1700
Data Index: 3186659 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3911. Min Act: -0.1700
Data Index: 7984150 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.3911. Min Act: -0.1700
Data Index: 3393334 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2973. Min Act: -0.1700
Data Index: 6355286 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2973. Min Act: -0.1700
Data Index: 1386347 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2973. Min Act: -0.1700
Data Index: 5570146 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2661. Min Act: -0.1700
Data Index: 3494459 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2661. Min Act: -0.1700
Data Index: 8241209 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2661. Min Act: -0.1700
Data Index: 3398641 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2661. Min Act: -0.1700
Data Index: 6669219 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2036. Min Act: -0.1700
Data Index: 4894689 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2036. Min Act: -0.1700
Data Index: 330334 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7348. Min Range: -5.7348
Max Act: 5.2036. Min Act: -0.1700
Data Index: 3519274 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19