Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4312 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.8302. Min Act: -0.1700
Data Index: 792153 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.8302. Min Act: -0.1700
Data Index: 5314541 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.4552. Min Act: -0.1700
Data Index: 3670081 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.4552. Min Act: -0.1700
Data Index: 2562265 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.3614. Min Act: -0.1700
Data Index: 2763143 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.3302. Min Act: -0.1700
Data Index: 2520810 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.3302. Min Act: -0.1700
Data Index: 8296981 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.3302. Min Act: -0.1700
Data Index: 6040082 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2989. Min Act: -0.1700
Data Index: 7851077 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2677. Min Act: -0.1700
Data Index: 8307114 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2364. Min Act: -0.1700
Data Index: 8130921 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2364. Min Act: -0.1700
Data Index: 4466776 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2364. Min Act: -0.1700
Data Index: 2571965 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2364. Min Act: -0.1700
Data Index: 1939913 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2364. Min Act: -0.1700
Data Index: 7637802 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2364. Min Act: -0.1700
Data Index: 5796874 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2052. Min Act: -0.1700
Data Index: 3636633 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2052. Min Act: -0.1700
Data Index: 249533 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2052. Min Act: -0.1700
Data Index: 6226702 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8302. Min Range: -7.8302
Max Act: 7.2052. Min Act: -0.1700
Data Index: 2624811 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19