Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.5543. Min Act: -0.1700
Data Index: 6539817 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.3355. Min Act: -0.1700
Data Index: 585296 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.2418. Min Act: -0.1700
Data Index: 1522284 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.1168. Min Act: -0.1700
Data Index: 3156321 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.1480. Min Act: -0.1700
Data Index: 1929132 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.1480. Min Act: -0.1700
Data Index: 1177676 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.1168. Min Act: -0.1700
Data Index: 4762619 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.1168. Min Act: -0.1700
Data Index: 8678351 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.0855. Min Act: -0.1700
Data Index: 3373847 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.0230. Min Act: -0.1700
Data Index: 6420046 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5543. Min Range: -5.5543
Max Act: 5.0230. Min Act: -0.1700
Data Index: 2779383 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5543. Min Range: -5.5543
Max Act: 4.9918. Min Act: -0.1700
Data Index: 2938157 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5543. Min Range: -5.5543
Max Act: 4.9918. Min Act: -0.1700
Data Index: 3174683 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5543. Min Range: -5.5543
Max Act: 4.9918. Min Act: -0.1700
Data Index: 4766611 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5543. Min Range: -5.5543
Max Act: 4.9605. Min Act: -0.1700
Data Index: 1177677 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5543. Min Range: -5.5543
Max Act: 4.9293. Min Act: -0.1700
Data Index: 5777540 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5543. Min Range: -5.5543
Max Act: 4.8980. Min Act: -0.1700
Data Index: 3626476 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5543. Min Range: -5.5543
Max Act: 4.9293. Min Act: -0.1700
Data Index: 177078 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5543. Min Range: -5.5543
Max Act: 4.9293. Min Act: -0.1700
Data Index: 6298647 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5543. Min Range: -5.5543
Max Act: 4.8980. Min Act: -0.1700
Data Index: 703903 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19