Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2364 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.3523. Min Act: -0.1700
Data Index: 2989446 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.3523. Min Act: -0.1700
Data Index: 6045284 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.3523. Min Act: -0.1700
Data Index: 260272 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.3523. Min Act: -0.1700
Data Index: 5047314 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.3523. Min Act: -0.1700
Data Index: 8150595 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2898. Min Act: -0.1700
Data Index: 5407028 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2898. Min Act: -0.1700
Data Index: 338696 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2585. Min Act: -0.1700
Data Index: 4777528 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2585. Min Act: -0.1700
Data Index: 6406709 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2585. Min Act: -0.1700
Data Index: 6514159 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2585. Min Act: -0.1700
Data Index: 8029354 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2585. Min Act: -0.1700
Data Index: 7776256 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2272. Min Act: -0.1700
Data Index: 2785160 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2272. Min Act: -0.1700
Data Index: 957538 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1960. Min Act: -0.1700
Data Index: 5026993 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2272. Min Act: -0.1700
Data Index: 5006520 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2585. Min Act: -0.1700
Data Index: 292298 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2272. Min Act: -0.1700
Data Index: 3874921 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.2272. Min Act: -0.1700
Data Index: 6748599 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3523. Min Range: -4.3523
Max Act: 4.1960. Min Act: -0.1700
Data Index: 870833 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19