Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2543 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.5490. Min Act: -0.1700
Data Index: 6047449 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.4865. Min Act: -0.1700
Data Index: 3016146 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.4240. Min Act: -0.1700
Data Index: 554733 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.4240. Min Act: -0.1700
Data Index: 2161392 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.3928. Min Act: -0.1700
Data Index: 5458442 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.3615. Min Act: -0.1700
Data Index: 1015851 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.2990. Min Act: -0.1700
Data Index: 7265724 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.2678. Min Act: -0.1700
Data Index: 8156639 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.2365. Min Act: -0.1700
Data Index: 215773 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.2365. Min Act: -0.1700
Data Index: 4256142 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.2365. Min Act: -0.1700
Data Index: 2097671 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.1740. Min Act: -0.1700
Data Index: 5834476 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.1740. Min Act: -0.1700
Data Index: 3424024 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.1740. Min Act: -0.1700
Data Index: 1011071 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.1740. Min Act: -0.1700
Data Index: 8495117 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.1428. Min Act: -0.1700
Data Index: 5549282 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.1428. Min Act: -0.1700
Data Index: 2889609 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.1115. Min Act: -0.1700
Data Index: 4108036 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.1115. Min Act: -0.1700
Data Index: 1714840 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5490. Min Range: -6.5490
Max Act: 6.1740. Min Act: -0.1700
Data Index: 2518114 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19