Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3262 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3636. Min Range: -7.3636
Max Act: 7.3636. Min Act: -0.1700
Data Index: 5634129 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3636. Min Range: -7.3636
Max Act: 7.2386. Min Act: -0.1700
Data Index: 6915933 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3636. Min Range: -7.3636
Max Act: 7.1448. Min Act: -0.1700
Data Index: 2699460 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3636. Min Range: -7.3636
Max Act: 7.1761. Min Act: -0.1700
Data Index: 3573642 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3636. Min Range: -7.3636
Max Act: 7.0823. Min Act: -0.1700
Data Index: 8734377 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3636. Min Range: -7.3636
Max Act: 7.0823. Min Act: -0.1700
Data Index: 6448245 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3636. Min Range: -7.3636
Max Act: 7.0511. Min Act: -0.1700
Data Index: 5634128 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.9886. Min Act: -0.1700
Data Index: 2354297 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.9261. Min Act: -0.1700
Data Index: 5593130 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.8948. Min Act: -0.1700
Data Index: 1919818 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.8636. Min Act: -0.1700
Data Index: 8656589 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.8011. Min Act: -0.1700
Data Index: 3241752 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.7698. Min Act: -0.1700
Data Index: 3310532 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.7386. Min Act: -0.1700
Data Index: 8628639 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.7073. Min Act: -0.1700
Data Index: 2059397 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.7073. Min Act: -0.1700
Data Index: 104788 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.6448. Min Act: -0.1700
Data Index: 5334555 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.7073. Min Act: -0.1700
Data Index: 2042304 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.6761. Min Act: -0.1700
Data Index: 8485358 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3636. Min Range: -7.3636
Max Act: 6.6448. Min Act: -0.1700
Data Index: 3306817 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19