Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2373 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1475. Min Range: -4.1475
Max Act: 4.1475. Min Act: -0.1700
Data Index: 4664762 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1475. Min Range: -4.1475
Max Act: 4.1162. Min Act: -0.1700
Data Index: 2481191 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1475. Min Range: -4.1475
Max Act: 4.0849. Min Act: -0.1700
Data Index: 3103467 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1475. Min Range: -4.1475
Max Act: 4.0224. Min Act: -0.1700
Data Index: 4059660 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9912. Min Act: -0.1700
Data Index: 7711138 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9912. Min Act: -0.1700
Data Index: 7316597 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9912. Min Act: -0.1700
Data Index: 6475282 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9599. Min Act: -0.1700
Data Index: 4059668 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9286. Min Act: -0.1700
Data Index: 2251726 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9286. Min Act: -0.1700
Data Index: 3488372 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9286. Min Act: -0.1700
Data Index: 1453171 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9286. Min Act: -0.1700
Data Index: 1156692 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9286. Min Act: -0.1700
Data Index: 3832294 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9286. Min Act: -0.1700
Data Index: 1156700 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.8974. Min Act: -0.1700
Data Index: 4416236 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.8974. Min Act: -0.1700
Data Index: 2251735 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9286. Min Act: -0.1700
Data Index: 1573138 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.9286. Min Act: -0.1700
Data Index: 3648347 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.8974. Min Act: -0.1700
Data Index: 2481185 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1475. Min Range: -4.1475
Max Act: 3.8974. Min Act: -0.1700
Data Index: 7316599 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19