Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4001 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1301. Min Range: -4.1301
Max Act: 4.1301. Min Act: -0.1700
Data Index: 7121388 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1301. Min Range: -4.1301
Max Act: 4.0988. Min Act: -0.1700
Data Index: 1060219 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1301. Min Range: -4.1301
Max Act: 4.0988. Min Act: -0.1700
Data Index: 1060204 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1301. Min Range: -4.1301
Max Act: 4.0050. Min Act: -0.1700
Data Index: 1060212 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9738. Min Act: -0.1700
Data Index: 1547352 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9112. Min Act: -0.1700
Data Index: 1578065 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9425. Min Act: -0.1700
Data Index: 648010 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.9112. Min Act: -0.1700
Data Index: 2836302 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.8487. Min Act: -0.1700
Data Index: 1060209 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.8487. Min Act: -0.1700
Data Index: 8115065 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.8174. Min Act: -0.1700
Data Index: 3011152 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.8174. Min Act: -0.1700
Data Index: 1890212 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.8487. Min Act: -0.1700
Data Index: 4207923 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.8174. Min Act: -0.1700
Data Index: 5755382 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.8174. Min Act: -0.1700
Data Index: 886879 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.7862. Min Act: -0.1700
Data Index: 8490168 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.7862. Min Act: -0.1700
Data Index: 3201414 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.7862. Min Act: -0.1700
Data Index: 5922779 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.7862. Min Act: -0.1700
Data Index: 5283425 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1301. Min Range: -4.1301
Max Act: 3.7549. Min Act: -0.1700
Data Index: 1337518 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19