Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3126 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.5449. Min Act: -0.1700
Data Index: 2443252 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.4199. Min Act: -0.1700
Data Index: 4828921 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.3887. Min Act: -0.1700
Data Index: 3818456 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.3574. Min Act: -0.1700
Data Index: 359676 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.3262. Min Act: -0.1700
Data Index: 7915981 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.3262. Min Act: -0.1700
Data Index: 1678914 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2637. Min Act: -0.1700
Data Index: 7721027 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2949. Min Act: -0.1700
Data Index: 3806187 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2637. Min Act: -0.1700
Data Index: 8209957 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2949. Min Act: -0.1700
Data Index: 6474524 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2637. Min Act: -0.1700
Data Index: 1659523 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2324. Min Act: -0.1700
Data Index: 3474475 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2324. Min Act: -0.1700
Data Index: 3994933 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2324. Min Act: -0.1700
Data Index: 5392213 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2324. Min Act: -0.1700
Data Index: 4770854 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2324. Min Act: -0.1700
Data Index: 3273161 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2324. Min Act: -0.1700
Data Index: 3294110 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2012. Min Act: -0.1700
Data Index: 6848683 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2012. Min Act: -0.1700
Data Index: 648767 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5449. Min Range: -4.5449
Max Act: 4.2012. Min Act: -0.1700
Data Index: 2986487 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19