Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3205 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1247. Min Range: -5.1247
Max Act: 5.1247. Min Act: -0.1700
Data Index: 4877831 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.9997. Min Act: -0.1700
Data Index: 2210195 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.9372. Min Act: -0.1700
Data Index: 7959786 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.9372. Min Act: -0.1700
Data Index: 6568662 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.9372. Min Act: -0.1700
Data Index: 7825402 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.9060. Min Act: -0.1700
Data Index: 2054255 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.8747. Min Act: -0.1700
Data Index: 5957963 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.8747. Min Act: -0.1700
Data Index: 1844125 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.8122. Min Act: -0.1700
Data Index: 4993312 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.8435. Min Act: -0.1700
Data Index: 3613245 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.8435. Min Act: -0.1700
Data Index: 307253 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.8435. Min Act: -0.1700
Data Index: 7267445 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.8122. Min Act: -0.1700
Data Index: 7749518 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.7810. Min Act: -0.1700
Data Index: 1044669 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.7810. Min Act: -0.1700
Data Index: 807986 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.7810. Min Act: -0.1700
Data Index: 3032723 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.7497. Min Act: -0.1700
Data Index: 1449800 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.7497. Min Act: -0.1700
Data Index: 4173936 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.7497. Min Act: -0.1700
Data Index: 6004751 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1247. Min Range: -5.1247
Max Act: 4.7497. Min Act: -0.1700
Data Index: 4855804 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19