Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 953 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.9290. Min Act: -0.1700
Data Index: 2973129 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.6790. Min Act: -0.1700
Data Index: 6865956 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.6165. Min Act: -0.1700
Data Index: 5848223 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.6165. Min Act: -0.1700
Data Index: 3997739 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.3665. Min Act: -0.1700
Data Index: 7092453 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.3040. Min Act: -0.1700
Data Index: 1163337 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.2415. Min Act: -0.1700
Data Index: 2254502 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.3040. Min Act: -0.1700
Data Index: 5749719 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.2415. Min Act: -0.1700
Data Index: 5158251 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.2415. Min Act: -0.1700
Data Index: 8202881 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.2415. Min Act: -0.1700
Data Index: 7131433 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.1790. Min Act: -0.1700
Data Index: 7099630 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.1790. Min Act: -0.1700
Data Index: 5249168 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.1790. Min Act: -0.1700
Data Index: 6713211 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.1165. Min Act: -0.1700
Data Index: 80792 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.1165. Min Act: -0.1700
Data Index: 4716194 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.0540. Min Act: -0.1700
Data Index: 5738887 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.0540. Min Act: -0.1700
Data Index: 4152737 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.0540. Min Act: -0.1700
Data Index: 6307406 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9290. Min Range: -8.9290
Max Act: 8.0540. Min Act: -0.1700
Data Index: 5755117 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19