Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2959 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.8742. Min Act: -0.1700
Data Index: 6901089 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.6242. Min Act: -0.1700
Data Index: 3089470 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.5617. Min Act: -0.1700
Data Index: 8550173 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.5617. Min Act: -0.1700
Data Index: 7582757 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.4367. Min Act: -0.1700
Data Index: 3374808 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.4367. Min Act: -0.1700
Data Index: 812205 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.4367. Min Act: -0.1700
Data Index: 3944376 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.2492. Min Act: -0.1700
Data Index: 2160520 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.1867. Min Act: -0.1700
Data Index: 6078836 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.1867. Min Act: -0.1700
Data Index: 7568969 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.1242. Min Act: -0.1700
Data Index: 2639616 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.1242. Min Act: -0.1700
Data Index: 1717411 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.1242. Min Act: -0.1700
Data Index: 7676831 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.1242. Min Act: -0.1700
Data Index: 5409866 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.1242. Min Act: -0.1700
Data Index: 3700352 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.1242. Min Act: -0.1700
Data Index: 8708246 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8742. Min Range: -8.8742
Max Act: 8.1242. Min Act: -0.1700
Data Index: 2931213 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8742. Min Range: -8.8742
Max Act: 7.9992. Min Act: -0.1700
Data Index: 4734538 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8742. Min Range: -8.8742
Max Act: 7.9992. Min Act: -0.1700
Data Index: 2533407 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8742. Min Range: -8.8742
Max Act: 7.9992. Min Act: -0.1700
Data Index: 5995994 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19