Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2717 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.6380. Min Act: -0.1700
Data Index: 1553724 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.5755. Min Act: -0.1700
Data Index: 4883046 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.5443. Min Act: -0.1700
Data Index: 7769682 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.4193. Min Act: -0.1700
Data Index: 4929887 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.3255. Min Act: -0.1700
Data Index: 4474631 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.3255. Min Act: -0.1700
Data Index: 7338528 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.2943. Min Act: -0.1700
Data Index: 3783075 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.2318. Min Act: -0.1700
Data Index: 6748853 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.2318. Min Act: -0.1700
Data Index: 7708879 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.2005. Min Act: -0.1700
Data Index: 5216795 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.2005. Min Act: -0.1700
Data Index: 5009555 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.1693. Min Act: -0.1700
Data Index: 6705718 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.1693. Min Act: -0.1700
Data Index: 637023 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.1068. Min Act: -0.1700
Data Index: 3523918 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.1380. Min Act: -0.1700
Data Index: 6137321 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.1380. Min Act: -0.1700
Data Index: 1248926 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.1380. Min Act: -0.1700
Data Index: 418539 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.1068. Min Act: -0.1700
Data Index: 6171501 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.1068. Min Act: -0.1700
Data Index: 4718851 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6380. Min Range: -6.6380
Max Act: 6.0755. Min Act: -0.1700
Data Index: 5820125 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19