Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 75 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.8268. Min Act: -0.1700
Data Index: 337004 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.5768. Min Act: -0.1700
Data Index: 1061781 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.5143. Min Act: -0.1700
Data Index: 7821755 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.2955. Min Act: -0.1700
Data Index: 4845847 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.2330. Min Act: -0.1700
Data Index: 2625450 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.2018. Min Act: -0.1700
Data Index: 934887 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.2018. Min Act: -0.1700
Data Index: 5098013 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.2018. Min Act: -0.1700
Data Index: 1686688 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.1393. Min Act: -0.1700
Data Index: 4674892 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.1705. Min Act: -0.1700
Data Index: 3248110 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.1705. Min Act: -0.1700
Data Index: 3614095 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.1080. Min Act: -0.1700
Data Index: 1225866 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.1393. Min Act: -0.1700
Data Index: 7819993 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.0768. Min Act: -0.1700
Data Index: 1311045 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.0768. Min Act: -0.1700
Data Index: 361466 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.0768. Min Act: -0.1700
Data Index: 8672791 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.0768. Min Act: -0.1700
Data Index: 361463 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.0455. Min Act: -0.1700
Data Index: 55369 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.0455. Min Act: -0.1700
Data Index: 7840298 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8268. Min Range: -5.8268
Max Act: 5.0768. Min Act: -0.1700
Data Index: 7962593 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19