Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.7185. Min Range: -9.7185
Max Act: 9.7185. Min Act: -0.1700
Data Index: 213419 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7185. Min Range: -9.7185
Max Act: 9.1560. Min Act: -0.1700
Data Index: 1463708 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7185. Min Range: -9.7185
Max Act: 9.0935. Min Act: -0.1700
Data Index: 4148615 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.9060. Min Act: -0.1700
Data Index: 4927021 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.9060. Min Act: -0.1700
Data Index: 1764030 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.9060. Min Act: -0.1700
Data Index: 4753635 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.8435. Min Act: -0.1700
Data Index: 819789 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.8435. Min Act: -0.1700
Data Index: 5502740 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.8435. Min Act: -0.1700
Data Index: 6237095 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.7810. Min Act: -0.1700
Data Index: 6320775 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.7810. Min Act: -0.1700
Data Index: 7098855 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.7810. Min Act: -0.1700
Data Index: 5640002 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.7810. Min Act: -0.1700
Data Index: 3288476 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.8435. Min Act: -0.1700
Data Index: 5744682 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.7185. Min Act: -0.1700
Data Index: 5811993 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.7185. Min Act: -0.1700
Data Index: 7932675 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.7185. Min Act: -0.1700
Data Index: 8744392 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.6560. Min Act: -0.1700
Data Index: 6871202 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.5935. Min Act: -0.1700
Data Index: 4762236 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7185. Min Range: -9.7185
Max Act: 8.5935. Min Act: -0.1700
Data Index: 5474034 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19