Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3237 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1989. Min Range: -6.1989
Max Act: 6.1989. Min Act: -0.1700
Data Index: 4083605 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1989. Min Range: -6.1989
Max Act: 6.1364. Min Act: -0.1700
Data Index: 1208704 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1989. Min Range: -6.1989
Max Act: 6.0427. Min Act: -0.1700
Data Index: 2018442 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1989. Min Range: -6.1989
Max Act: 6.0427. Min Act: -0.1700
Data Index: 2738611 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1989. Min Range: -6.1989
Max Act: 6.0427. Min Act: -0.1700
Data Index: 6579184 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.9802. Min Act: -0.1700
Data Index: 2166926 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.9177. Min Act: -0.1700
Data Index: 187519 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.9177. Min Act: -0.1700
Data Index: 6771880 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.9177. Min Act: -0.1700
Data Index: 1400018 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.9177. Min Act: -0.1700
Data Index: 7118968 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.8864. Min Act: -0.1700
Data Index: 8348150 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.8552. Min Act: -0.1700
Data Index: 6389678 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.8552. Min Act: -0.1700
Data Index: 1983196 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.8552. Min Act: -0.1700
Data Index: 5406839 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.8552. Min Act: -0.1700
Data Index: 6244872 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.8239. Min Act: -0.1700
Data Index: 228034 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.7927. Min Act: -0.1700
Data Index: 1259787 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.7927. Min Act: -0.1700
Data Index: 940259 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.7927. Min Act: -0.1700
Data Index: 2125218 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1989. Min Range: -6.1989
Max Act: 5.7927. Min Act: -0.1700
Data Index: 1822164 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19