Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2837. Min Range: -6.2837
Max Act: 6.2837. Min Act: -0.1700
Data Index: 6751485 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2837. Min Range: -6.2837
Max Act: 6.2212. Min Act: -0.1700
Data Index: 6640131 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.9712. Min Act: -0.1700
Data Index: 8283396 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.8462. Min Act: -0.1700
Data Index: 5917960 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.8462. Min Act: -0.1700
Data Index: 626704 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.8150. Min Act: -0.1700
Data Index: 6900759 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.8150. Min Act: -0.1700
Data Index: 6675607 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.7525. Min Act: -0.1700
Data Index: 5898280 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.7837. Min Act: -0.1700
Data Index: 7892726 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.7837. Min Act: -0.1700
Data Index: 5757144 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.7525. Min Act: -0.1700
Data Index: 2198272 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.6900. Min Act: -0.1700
Data Index: 3099718 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.7212. Min Act: -0.1700
Data Index: 7730145 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.6587. Min Act: -0.1700
Data Index: 2836453 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.6900. Min Act: -0.1700
Data Index: 6146610 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.6900. Min Act: -0.1700
Data Index: 3952494 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.6275. Min Act: -0.1700
Data Index: 2074757 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.6275. Min Act: -0.1700
Data Index: 4846614 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.5962. Min Act: -0.1700
Data Index: 4560429 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2837. Min Range: -6.2837
Max Act: 5.6275. Min Act: -0.1700
Data Index: 7898503 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19