Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.7443. Min Act: -0.1700
Data Index: 4249443 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.6818. Min Act: -0.1700
Data Index: 1108512 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.6193. Min Act: -0.1700
Data Index: 8168104 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.4943. Min Act: -0.1700
Data Index: 8156887 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.4943. Min Act: -0.1700
Data Index: 5566097 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.4943. Min Act: -0.1700
Data Index: 1149348 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.4943. Min Act: -0.1700
Data Index: 3193803 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.4318. Min Act: -0.1700
Data Index: 2577707 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.4006. Min Act: -0.1700
Data Index: 2126158 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.4006. Min Act: -0.1700
Data Index: 7568534 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.3693. Min Act: -0.1700
Data Index: 7442524 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.3381. Min Act: -0.1700
Data Index: 476744 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.3381. Min Act: -0.1700
Data Index: 7642649 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.3381. Min Act: -0.1700
Data Index: 1631623 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.3381. Min Act: -0.1700
Data Index: 8450031 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.2756. Min Act: -0.1700
Data Index: 2092265 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.3068. Min Act: -0.1700
Data Index: 4726312 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.3068. Min Act: -0.1700
Data Index: 3187767 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.2756. Min Act: -0.1700
Data Index: 6589459 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7443. Min Range: -7.7443
Max Act: 7.2443. Min Act: -0.1700
Data Index: 3567685 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19