Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.4345. Min Act: -0.1700
Data Index: 2635196 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.2470. Min Act: -0.1700
Data Index: 6443569 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0907. Min Act: -0.1700
Data Index: 7943912 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4345. Min Range: -5.4345
Max Act: 5.0595. Min Act: -0.1700
Data Index: 839925 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9970. Min Act: -0.1700
Data Index: 1363080 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9970. Min Act: -0.1700
Data Index: 5518294 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9657. Min Act: -0.1700
Data Index: 925043 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9970. Min Act: -0.1700
Data Index: 6943117 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9657. Min Act: -0.1700
Data Index: 2849593 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9345. Min Act: -0.1700
Data Index: 4610651 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9345. Min Act: -0.1700
Data Index: 4943974 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9345. Min Act: -0.1700
Data Index: 8537832 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9032. Min Act: -0.1700
Data Index: 3184110 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9032. Min Act: -0.1700
Data Index: 5404285 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.8720. Min Act: -0.1700
Data Index: 592705 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.9032. Min Act: -0.1700
Data Index: 1720552 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.8720. Min Act: -0.1700
Data Index: 5316748 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.8720. Min Act: -0.1700
Data Index: 3882556 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.8407. Min Act: -0.1700
Data Index: 2603130 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4345. Min Range: -5.4345
Max Act: 4.8407. Min Act: -0.1700
Data Index: 4390073 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19