Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4427 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.5425. Min Act: -0.1700
Data Index: 6881092 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.4172. Min Act: -0.1700
Data Index: 3102338 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.4485. Min Act: -0.1700
Data Index: 5286069 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.4172. Min Act: -0.1700
Data Index: 5323658 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.3702. Min Act: -0.1700
Data Index: 1527073 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.3388. Min Act: -0.1700
Data Index: 8361639 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.2760. Min Act: -0.1700
Data Index: 6340903 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.2760. Min Act: -0.1700
Data Index: 8340698 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.2446. Min Act: -0.1700
Data Index: 4541973 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.2289. Min Act: -0.1700
Data Index: 1836883 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.2289. Min Act: -0.1700
Data Index: 6727350 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.2131. Min Act: -0.1700
Data Index: 3331309 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.1974. Min Act: -0.1700
Data Index: 7254260 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.1817. Min Act: -0.1700
Data Index: 1581177 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.1817. Min Act: -0.1700
Data Index: 3182671 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.1660. Min Act: -0.1700
Data Index: 5014138 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.1660. Min Act: -0.1700
Data Index: 2782825 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.1660. Min Act: -0.1700
Data Index: 3180207 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.1660. Min Act: -0.1700
Data Index: 5339372 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5425. Min Range: -3.5425
Max Act: 3.1345. Min Act: -0.1700
Data Index: 5999042 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19