Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3936 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.4449. Min Act: -0.1700
Data Index: 671868 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.3633. Min Act: -0.1699
Data Index: 5937642 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.3469. Min Act: -0.1700
Data Index: 5080105 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.3141. Min Act: -0.1700
Data Index: 3215953 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.2976. Min Act: -0.1700
Data Index: 4461925 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.2976. Min Act: -0.1700
Data Index: 3140267 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.2976. Min Act: -0.1700
Data Index: 2295211 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.2647. Min Act: -0.1700
Data Index: 8216336 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.2647. Min Act: -0.1700
Data Index: 3500578 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.2316. Min Act: -0.1700
Data Index: 8476290 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.2316. Min Act: -0.1700
Data Index: 2029179 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.2151. Min Act: -0.1700
Data Index: 3016126 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.1985. Min Act: -0.1700
Data Index: 7279685 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.2151. Min Act: -0.1700
Data Index: 5510392 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.1819. Min Act: -0.1700
Data Index: 8523489 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.1985. Min Act: -0.1700
Data Index: 2774388 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.1985. Min Act: -0.1700
Data Index: 7507778 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.1985. Min Act: -0.1700
Data Index: 5986151 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.1985. Min Act: -0.1700
Data Index: 242591 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4449. Min Range: -2.4449
Max Act: 2.1819. Min Act: -0.1700
Data Index: 8020098 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19