Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0500. Min Range: -8.0500
Max Act: 8.0500. Min Act: -0.1700
Data Index: 2802693 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.7375. Min Act: -0.1700
Data Index: 4971184 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.7375. Min Act: -0.1700
Data Index: 7073671 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.7375. Min Act: -0.1700
Data Index: 8802346 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.6750. Min Act: -0.1700
Data Index: 5292427 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.6750. Min Act: -0.1700
Data Index: 5262475 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.6750. Min Act: -0.1700
Data Index: 1376952 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.6750. Min Act: -0.1700
Data Index: 8333311 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.5500. Min Act: -0.1700
Data Index: 1805536 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.5500. Min Act: -0.1700
Data Index: 8108678 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.5500. Min Act: -0.1700
Data Index: 3435624 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.5500. Min Act: -0.1700
Data Index: 1622114 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.5187. Min Act: -0.1700
Data Index: 2809018 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.5187. Min Act: -0.1700
Data Index: 5572541 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.4562. Min Act: -0.1700
Data Index: 6802381 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.4562. Min Act: -0.1700
Data Index: 6267683 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.4562. Min Act: -0.1700
Data Index: 7773658 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.4562. Min Act: -0.1700
Data Index: 6191421 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.3937. Min Act: -0.1700
Data Index: 3939458 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0500. Min Range: -8.0500
Max Act: 7.4250. Min Act: -0.1700
Data Index: 6814019 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19