Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2119. Min Range: -9.2119
Max Act: 9.2119. Min Act: -0.1700
Data Index: 2976381 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2119. Min Range: -9.2119
Max Act: 9.0869. Min Act: -0.1700
Data Index: 3342240 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2119. Min Range: -9.2119
Max Act: 9.0244. Min Act: -0.1700
Data Index: 2323810 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.9619. Min Act: -0.1700
Data Index: 2979659 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.9619. Min Act: -0.1700
Data Index: 8586797 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.8994. Min Act: -0.1700
Data Index: 4058516 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.9619. Min Act: -0.1700
Data Index: 8019195 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.7119. Min Act: -0.1700
Data Index: 3361136 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.7119. Min Act: -0.1700
Data Index: 2236761 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.6494. Min Act: -0.1700
Data Index: 2542354 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.6494. Min Act: -0.1700
Data Index: 2598386 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.6494. Min Act: -0.1700
Data Index: 1238234 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.5244. Min Act: -0.1700
Data Index: 4296539 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.5244. Min Act: -0.1700
Data Index: 8579403 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.5244. Min Act: -0.1700
Data Index: 2976382 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.5244. Min Act: -0.1700
Data Index: 3342236 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.4619. Min Act: -0.1700
Data Index: 3501000 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.3994. Min Act: -0.1700
Data Index: 7633771 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.3682. Min Act: -0.1700
Data Index: 3522741 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2119. Min Range: -9.2119
Max Act: 8.3682. Min Act: -0.1700
Data Index: 5676639 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19