Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 25 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0257. Min Range: -6.0257
Max Act: 6.0257. Min Act: -0.1700
Data Index: 7586139 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.9007. Min Act: -0.1700
Data Index: 3623752 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.8070. Min Act: -0.1700
Data Index: 1882315 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.8070. Min Act: -0.1700
Data Index: 5070584 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.8070. Min Act: -0.1700
Data Index: 7316957 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.8382. Min Act: -0.1700
Data Index: 5686226 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.8070. Min Act: -0.1700
Data Index: 1302841 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.7132. Min Act: -0.1700
Data Index: 2246373 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.6820. Min Act: -0.1700
Data Index: 709722 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.6507. Min Act: -0.1700
Data Index: 2252435 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.6507. Min Act: -0.1700
Data Index: 1785309 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.6195. Min Act: -0.1700
Data Index: 1982463 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.6195. Min Act: -0.1700
Data Index: 4541264 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.6195. Min Act: -0.1700
Data Index: 8761280 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.6195. Min Act: -0.1700
Data Index: 3248375 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.6195. Min Act: -0.1700
Data Index: 6205144 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.5882. Min Act: -0.1700
Data Index: 8797083 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.5882. Min Act: -0.1700
Data Index: 5709473 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.5882. Min Act: -0.1700
Data Index: 5748716 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0257. Min Range: -6.0257
Max Act: 5.5570. Min Act: -0.1700
Data Index: 4967362 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19