Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4644 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.6982. Min Act: -0.1700
Data Index: 2385459 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.5697. Min Act: -0.1699
Data Index: 4427236 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.5536. Min Act: -0.1700
Data Index: 6108348 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.4401. Min Act: -0.1700
Data Index: 1885713 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.3912. Min Act: -0.1700
Data Index: 4315700 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.3257. Min Act: -0.1700
Data Index: 2139264 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.3257. Min Act: -0.1700
Data Index: 7654800 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.3093. Min Act: -0.1700
Data Index: 2178310 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2929. Min Act: -0.1700
Data Index: 1317568 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2929. Min Act: -0.1700
Data Index: 6706206 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2764. Min Act: -0.1700
Data Index: 5389837 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2764. Min Act: -0.1674
Data Index: 4999301 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2929. Min Act: -0.1700
Data Index: 8119281 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2764. Min Act: -0.1698
Data Index: 6099509 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2434. Min Act: -0.1700
Data Index: 3458229 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2599. Min Act: -0.1700
Data Index: 136269 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2434. Min Act: -0.1700
Data Index: 3976619 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2103. Min Act: -0.1698
Data Index: 2014124 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2103. Min Act: -0.1700
Data Index: 5376855 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6982. Min Range: -2.6982
Max Act: 2.2103. Min Act: -0.1698
Data Index: 2241550 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19