Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.8424. Min Act: -0.1700
Data Index: 5016512 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.7174. Min Act: -0.1700
Data Index: 1961237 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.5924. Min Act: -0.1700
Data Index: 2426624 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.2487. Min Act: -0.1700
Data Index: 2040206 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.1862. Min Act: -0.1700
Data Index: 6529194 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.1237. Min Act: -0.1700
Data Index: 7254887 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.0924. Min Act: -0.1700
Data Index: 2206680 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.0924. Min Act: -0.1700
Data Index: 1693686 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.0612. Min Act: -0.1700
Data Index: 2089498 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.0612. Min Act: -0.1700
Data Index: 714559 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.0612. Min Act: -0.1700
Data Index: 761563 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8424. Min Range: -6.8424
Max Act: 6.0299. Min Act: -0.1700
Data Index: 6934058 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8424. Min Range: -6.8424
Max Act: 5.9987. Min Act: -0.1700
Data Index: 8467872 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8424. Min Range: -6.8424
Max Act: 5.9674. Min Act: -0.1700
Data Index: 5770051 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8424. Min Range: -6.8424
Max Act: 5.9362. Min Act: -0.1700
Data Index: 971364 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8424. Min Range: -6.8424
Max Act: 5.9049. Min Act: -0.1700
Data Index: 803696 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8424. Min Range: -6.8424
Max Act: 5.9049. Min Act: -0.1700
Data Index: 2798285 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8424. Min Range: -6.8424
Max Act: 5.9049. Min Act: -0.1700
Data Index: 8756334 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8424. Min Range: -6.8424
Max Act: 5.8737. Min Act: -0.1700
Data Index: 4139504 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8424. Min Range: -6.8424
Max Act: 5.8737. Min Act: -0.1700
Data Index: 3803658 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19