Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4928 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1339. Min Range: -8.1339
Max Act: 8.1339. Min Act: -0.1700
Data Index: 5298701 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.9152. Min Act: -0.1700
Data Index: 687369 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.3214. Min Act: -0.1700
Data Index: 3056467 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.2902. Min Act: -0.1700
Data Index: 216318 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.2589. Min Act: -0.1700
Data Index: 1670374 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.2277. Min Act: -0.1700
Data Index: 6338215 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.2277. Min Act: -0.1700
Data Index: 5997236 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.1964. Min Act: -0.1700
Data Index: 5826409 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.1652. Min Act: -0.1700
Data Index: 1103395 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.1339. Min Act: -0.1700
Data Index: 2515693 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.1339. Min Act: -0.1700
Data Index: 6729292 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.0714. Min Act: -0.1700
Data Index: 7954500 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.0714. Min Act: -0.1700
Data Index: 5248128 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.0402. Min Act: -0.1700
Data Index: 2191662 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.0402. Min Act: -0.1700
Data Index: 1236469 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.0089. Min Act: -0.1700
Data Index: 3356802 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.0089. Min Act: -0.1700
Data Index: 7099447 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.0089. Min Act: -0.1700
Data Index: 3789472 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1339. Min Range: -8.1339
Max Act: 7.0089. Min Act: -0.1700
Data Index: 4541521 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1339. Min Range: -8.1339
Max Act: 6.9464. Min Act: -0.1700
Data Index: 6996527 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19