Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3762 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2487. Min Act: -0.1700
Data Index: 3281294 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2330. Min Act: -0.1700
Data Index: 7789660 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.2015. Min Act: -0.1700
Data Index: 3282248 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1858. Min Act: -0.1700
Data Index: 938067 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1543. Min Act: -0.1700
Data Index: 2264002 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1701. Min Act: -0.1700
Data Index: 4147187 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1543. Min Act: -0.1699
Data Index: 915914 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1543. Min Act: -0.1699
Data Index: 3527460 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1386. Min Act: -0.1700
Data Index: 5457365 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1386. Min Act: -0.1700
Data Index: 3708389 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1386. Min Act: -0.1700
Data Index: 4103102 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1071. Min Act: -0.1700
Data Index: 3720315 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1228. Min Act: -0.1700
Data Index: 6259787 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1228. Min Act: -0.1700
Data Index: 8485487 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1071. Min Act: -0.1700
Data Index: 1529721 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.0913. Min Act: -0.1700
Data Index: 508822 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.0913. Min Act: -0.1700
Data Index: 3200364 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.0913. Min Act: -0.1700
Data Index: 6592530 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.0913. Min Act: -0.1700
Data Index: 2222726 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2487. Min Range: -3.2487
Max Act: 3.1071. Min Act: -0.1700
Data Index: 2601768 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19