Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5724 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.4570. Min Act: -0.1700
Data Index: 1173508 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.5195. Min Act: -0.1700
Data Index: 4063607 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.4883. Min Act: -0.1700
Data Index: 507533 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.4258. Min Act: -0.1700
Data Index: 5187317 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.3008. Min Act: -0.1700
Data Index: 7278472 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.2383. Min Act: -0.1700
Data Index: 1815933 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.2383. Min Act: -0.1700
Data Index: 1258265 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.2383. Min Act: -0.1700
Data Index: 5162172 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.1445. Min Act: -0.1700
Data Index: 6262040 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.2070. Min Act: -0.1700
Data Index: 7870010 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.1758. Min Act: -0.1700
Data Index: 8078037 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.1758. Min Act: -0.1700
Data Index: 6835982 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.1445. Min Act: -0.1700
Data Index: 6620396 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.1445. Min Act: -0.1700
Data Index: 7783312 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.1133. Min Act: -0.1700
Data Index: 532466 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.1133. Min Act: -0.1700
Data Index: 4499829 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.1133. Min Act: -0.1700
Data Index: 3810808 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.0820. Min Act: -0.1700
Data Index: 4187265 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.0820. Min Act: -0.1700
Data Index: 6654917 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5195. Min Range: -7.5195
Max Act: 7.0195. Min Act: -0.1700
Data Index: 3516964 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19