Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2612. Min Range: -9.2612
Max Act: 9.2612. Min Act: -0.1700
Data Index: 646944 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2612. Min Range: -9.2612
Max Act: 9.1987. Min Act: -0.1700
Data Index: 4749887 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2612. Min Range: -9.2612
Max Act: 9.1362. Min Act: -0.1700
Data Index: 6814370 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.6987. Min Act: -0.1700
Data Index: 6339484 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.6362. Min Act: -0.1700
Data Index: 1112438 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.5737. Min Act: -0.1700
Data Index: 3527850 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.4487. Min Act: -0.1700
Data Index: 7058237 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.4487. Min Act: -0.1700
Data Index: 2061527 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.3862. Min Act: -0.1700
Data Index: 744288 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.3237. Min Act: -0.1700
Data Index: 3633870 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.2612. Min Act: -0.1700
Data Index: 722154 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.2299. Min Act: -0.1700
Data Index: 324857 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.2299. Min Act: -0.1700
Data Index: 5107556 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.2299. Min Act: -0.1700
Data Index: 5302420 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.2299. Min Act: -0.1700
Data Index: 5396760 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.1987. Min Act: -0.1700
Data Index: 1765308 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.2299. Min Act: -0.1700
Data Index: 3046475 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.1987. Min Act: -0.1700
Data Index: 7216569 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.1987. Min Act: -0.1700
Data Index: 3939986 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2612. Min Range: -9.2612
Max Act: 8.1362. Min Act: -0.1700
Data Index: 4720860 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19