Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 866 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.4503. Min Act: -0.1700
Data Index: 4868765 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.4177. Min Act: -0.1700
Data Index: 5895745 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.4177. Min Act: -0.1700
Data Index: 2789157 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3687. Min Act: -0.1700
Data Index: 3333436 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3851. Min Act: -0.1700
Data Index: 6076950 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3523. Min Act: -0.1700
Data Index: 3775118 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3523. Min Act: -0.1700
Data Index: 4796140 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3360. Min Act: -0.1700
Data Index: 1477308 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3360. Min Act: -0.1700
Data Index: 2216526 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3360. Min Act: -0.1700
Data Index: 4820973 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3360. Min Act: -0.1700
Data Index: 3106006 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3195. Min Act: -0.1700
Data Index: 243055 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3031. Min Act: -0.1700
Data Index: 5044603 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3195. Min Act: -0.1700
Data Index: 8349623 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3031. Min Act: -0.1700
Data Index: 2220708 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.2866. Min Act: -0.1700
Data Index: 3336015 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.2866. Min Act: -0.1700
Data Index: 33002 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3031. Min Act: -0.1700
Data Index: 6550624 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3031. Min Act: -0.1700
Data Index: 3459707 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4503. Min Range: -2.4503
Max Act: 2.3031. Min Act: -0.1700
Data Index: 3255621 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19