Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3984 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.4603. Min Act: -0.1700
Data Index: 2708120 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.3666. Min Act: -0.1700
Data Index: 1613306 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.3041. Min Act: -0.1700
Data Index: 5233952 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.2416. Min Act: -0.1700
Data Index: 4699115 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.2728. Min Act: -0.1700
Data Index: 4607150 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.1791. Min Act: -0.1700
Data Index: 2846812 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.1166. Min Act: -0.1700
Data Index: 3699498 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.1166. Min Act: -0.1700
Data Index: 3112757 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.1166. Min Act: -0.1700
Data Index: 4919903 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.0853. Min Act: -0.1700
Data Index: 516569 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.0541. Min Act: -0.1700
Data Index: 6921204 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.0541. Min Act: -0.1700
Data Index: 6759829 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.0541. Min Act: -0.1700
Data Index: 348653 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4603. Min Range: -5.4603
Max Act: 5.0228. Min Act: -0.1700
Data Index: 938934 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4603. Min Range: -5.4603
Max Act: 4.9916. Min Act: -0.1700
Data Index: 8598780 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4603. Min Range: -5.4603
Max Act: 4.9916. Min Act: -0.1700
Data Index: 3767219 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4603. Min Range: -5.4603
Max Act: 4.9916. Min Act: -0.1700
Data Index: 7730627 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4603. Min Range: -5.4603
Max Act: 4.9916. Min Act: -0.1700
Data Index: 1460663 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4603. Min Range: -5.4603
Max Act: 4.9603. Min Act: -0.1700
Data Index: 6858240 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4603. Min Range: -5.4603
Max Act: 4.9291. Min Act: -0.1700
Data Index: 712216 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19