Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4635 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2609. Min Range: -4.2609
Max Act: 4.2609. Min Act: -0.1700
Data Index: 7943431 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2609. Min Range: -4.2609
Max Act: 4.0421. Min Act: -0.1700
Data Index: 6396691 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2609. Min Range: -4.2609
Max Act: 4.0421. Min Act: -0.1700
Data Index: 3630824 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.9796. Min Act: -0.1700
Data Index: 7721991 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.9483. Min Act: -0.1700
Data Index: 4449684 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.9171. Min Act: -0.1700
Data Index: 2479592 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.9171. Min Act: -0.1700
Data Index: 7513304 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.8858. Min Act: -0.1700
Data Index: 5250294 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.9171. Min Act: -0.1700
Data Index: 126383 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.8858. Min Act: -0.1700
Data Index: 1687486 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.8545. Min Act: -0.1700
Data Index: 1283445 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.8545. Min Act: -0.1700
Data Index: 7538394 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.8233. Min Act: -0.1700
Data Index: 4780704 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.8233. Min Act: -0.1700
Data Index: 3804770 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.8233. Min Act: -0.1700
Data Index: 8600750 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.8233. Min Act: -0.1700
Data Index: 5710238 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.8233. Min Act: -0.1700
Data Index: 1178599 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.7920. Min Act: -0.1700
Data Index: 7688980 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.7920. Min Act: -0.1700
Data Index: 1178600 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2609. Min Range: -4.2609
Max Act: 3.7920. Min Act: -0.1700
Data Index: 5283925 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19