Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 720 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.3383. Min Act: -0.1700
Data Index: 1605893 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.2445. Min Act: -0.1700
Data Index: 3180509 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.1508. Min Act: -0.1700
Data Index: 3153697 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.1195. Min Act: -0.1700
Data Index: 6976571 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.0883. Min Act: -0.1700
Data Index: 3187965 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.0883. Min Act: -0.1700
Data Index: 1059530 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.0570. Min Act: -0.1700
Data Index: 2245335 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.0257. Min Act: -0.1700
Data Index: 7722870 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.0257. Min Act: -0.1700
Data Index: 2172219 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.0257. Min Act: -0.1700
Data Index: 3952540 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3383. Min Range: -4.3383
Max Act: 4.0257. Min Act: -0.1700
Data Index: 1653243 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3383. Min Range: -4.3383
Max Act: 3.9945. Min Act: -0.1700
Data Index: 7493720 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3383. Min Range: -4.3383
Max Act: 3.9945. Min Act: -0.1700
Data Index: 6044128 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3383. Min Range: -4.3383
Max Act: 3.9945. Min Act: -0.1700
Data Index: 5490382 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3383. Min Range: -4.3383
Max Act: 3.9945. Min Act: -0.1700
Data Index: 76116 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3383. Min Range: -4.3383
Max Act: 3.9945. Min Act: -0.1700
Data Index: 1250056 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3383. Min Range: -4.3383
Max Act: 3.9945. Min Act: -0.1700
Data Index: 7659539 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3383. Min Range: -4.3383
Max Act: 3.9945. Min Act: -0.1700
Data Index: 5271772 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3383. Min Range: -4.3383
Max Act: 3.9632. Min Act: -0.1700
Data Index: 258933 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3383. Min Range: -4.3383
Max Act: 3.9319. Min Act: -0.1700
Data Index: 5716789 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19