Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3672 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1772. Min Range: -8.1772
Max Act: 8.1772. Min Act: -0.1700
Data Index: 7197358 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.9897. Min Act: -0.1700
Data Index: 8526857 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.9897. Min Act: -0.1700
Data Index: 6138253 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.8022. Min Act: -0.1700
Data Index: 858868 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.7397. Min Act: -0.1700
Data Index: 5903409 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.7397. Min Act: -0.1700
Data Index: 4466642 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.7397. Min Act: -0.1700
Data Index: 7601410 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.6772. Min Act: -0.1700
Data Index: 5575864 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.6772. Min Act: -0.1700
Data Index: 6350293 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.6147. Min Act: -0.1700
Data Index: 1701673 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.6147. Min Act: -0.1700
Data Index: 5785186 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.5522. Min Act: -0.1700
Data Index: 6468264 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.6147. Min Act: -0.1700
Data Index: 2667162 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.4897. Min Act: -0.1700
Data Index: 6380938 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.5522. Min Act: -0.1700
Data Index: 1441138 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.5522. Min Act: -0.1700
Data Index: 7362944 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.4897. Min Act: -0.1700
Data Index: 1701658 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.4897. Min Act: -0.1700
Data Index: 1943051 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.4897. Min Act: -0.1700
Data Index: 1024415 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1772. Min Range: -8.1772
Max Act: 7.4272. Min Act: -0.1700
Data Index: 595554 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19