Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3896 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2550. Min Range: -9.2550
Max Act: 9.2550. Min Act: -0.1700
Data Index: 966624 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2550. Min Range: -9.2550
Max Act: 9.0050. Min Act: -0.1700
Data Index: 7973021 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2550. Min Range: -9.2550
Max Act: 9.0050. Min Act: -0.1700
Data Index: 4873503 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2550. Min Range: -9.2550
Max Act: 9.0050. Min Act: -0.1700
Data Index: 8291191 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2550. Min Range: -9.2550
Max Act: 9.0050. Min Act: -0.1700
Data Index: 5976175 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.8800. Min Act: -0.1700
Data Index: 7890280 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.9425. Min Act: -0.1700
Data Index: 4607810 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.8800. Min Act: -0.1700
Data Index: 217037 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.8175. Min Act: -0.1700
Data Index: 5065266 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.8175. Min Act: -0.1700
Data Index: 8666733 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.8175. Min Act: -0.1700
Data Index: 8571026 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.8175. Min Act: -0.1700
Data Index: 180919 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.8175. Min Act: -0.1700
Data Index: 4607805 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.8175. Min Act: -0.1700
Data Index: 2875778 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.7550. Min Act: -0.1700
Data Index: 2950780 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.7550. Min Act: -0.1700
Data Index: 5145144 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.7550. Min Act: -0.1700
Data Index: 498025 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.6925. Min Act: -0.1700
Data Index: 7103908 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.7550. Min Act: -0.1700
Data Index: 7973907 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2550. Min Range: -9.2550
Max Act: 8.6925. Min Act: -0.1700
Data Index: 1564611 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19