Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1945 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5494. Min Range: -6.5494
Max Act: 6.5494. Min Act: -0.1700
Data Index: 4014646 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5494. Min Range: -6.5494
Max Act: 6.4244. Min Act: -0.1700
Data Index: 126137 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5494. Min Range: -6.5494
Max Act: 6.2994. Min Act: -0.1700
Data Index: 585967 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5494. Min Range: -6.5494
Max Act: 6.2369. Min Act: -0.1700
Data Index: 6555023 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5494. Min Range: -6.5494
Max Act: 6.0181. Min Act: -0.1700
Data Index: 3322248 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.9869. Min Act: -0.1700
Data Index: 8544855 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.9244. Min Act: -0.1700
Data Index: 1953584 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.9244. Min Act: -0.1700
Data Index: 2792166 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.9244. Min Act: -0.1700
Data Index: 1876888 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.8931. Min Act: -0.1700
Data Index: 6533798 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 5489584 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.8931. Min Act: -0.1700
Data Index: 3932638 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 2750597 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 8071389 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 157962 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 7735115 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.8619. Min Act: -0.1700
Data Index: 3804413 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.8306. Min Act: -0.1700
Data Index: 6482651 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.7994. Min Act: -0.1700
Data Index: 4426190 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5494. Min Range: -6.5494
Max Act: 5.7994. Min Act: -0.1700
Data Index: 4173548 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19