Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3134 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6886. Min Range: -9.6886
Max Act: 9.6886. Min Act: -0.1700
Data Index: 3615040 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6886. Min Range: -9.6886
Max Act: 9.5636. Min Act: -0.1700
Data Index: 5139409 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6886. Min Range: -9.6886
Max Act: 9.5011. Min Act: -0.1700
Data Index: 848881 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6886. Min Range: -9.6886
Max Act: 9.3761. Min Act: -0.1700
Data Index: 7634473 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.8761. Min Act: -0.1700
Data Index: 1482213 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.8136. Min Act: -0.1700
Data Index: 5736302 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.7511. Min Act: -0.1700
Data Index: 102837 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.7511. Min Act: -0.1700
Data Index: 2077290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.6886. Min Act: -0.1700
Data Index: 3076710 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.6886. Min Act: -0.1700
Data Index: 2506747 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.6886. Min Act: -0.1700
Data Index: 8298860 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.6261. Min Act: -0.1700
Data Index: 2718037 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.5636. Min Act: -0.1700
Data Index: 6107824 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.5636. Min Act: -0.1700
Data Index: 8020270 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.5011. Min Act: -0.1700
Data Index: 8105950 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.4386. Min Act: -0.1700
Data Index: 3301911 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.4386. Min Act: -0.1700
Data Index: 6460277 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.3136. Min Act: -0.1700
Data Index: 4507545 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.3136. Min Act: -0.1700
Data Index: 3082240 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6886. Min Range: -9.6886
Max Act: 8.2511. Min Act: -0.1700
Data Index: 2749246 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19