Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3229 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.8146. Min Act: -0.1700
Data Index: 3055705 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.6896. Min Act: -0.1700
Data Index: 7547727 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.5021. Min Act: -0.1700
Data Index: 1879402 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.3146. Min Act: -0.1700
Data Index: 7370117 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.2521. Min Act: -0.1700
Data Index: 1131378 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.2209. Min Act: -0.1700
Data Index: 5260905 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.2209. Min Act: -0.1700
Data Index: 1575273 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.1584. Min Act: -0.1700
Data Index: 2731349 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.1584. Min Act: -0.1700
Data Index: 547240 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.1271. Min Act: -0.1700
Data Index: 6728465 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.1271. Min Act: -0.1700
Data Index: 2988159 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.1271. Min Act: -0.1700
Data Index: 5480146 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.0646. Min Act: -0.1700
Data Index: 401567 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.0646. Min Act: -0.1700
Data Index: 3543938 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.0021. Min Act: -0.1700
Data Index: 6039278 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8146. Min Range: -7.8146
Max Act: 6.9396. Min Act: -0.1700
Data Index: 817036 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8146. Min Range: -7.8146
Max Act: 7.0021. Min Act: -0.1700
Data Index: 8217403 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8146. Min Range: -7.8146
Max Act: 6.9709. Min Act: -0.1700
Data Index: 6182550 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8146. Min Range: -7.8146
Max Act: 6.9709. Min Act: -0.1700
Data Index: 6056408 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8146. Min Range: -7.8146
Max Act: 6.8771. Min Act: -0.1700
Data Index: 6330010 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19