Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3270 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1069. Min Range: -6.1069
Max Act: 6.1069. Min Act: -0.1700
Data Index: 2303883 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1069. Min Range: -6.1069
Max Act: 6.0132. Min Act: -0.1700
Data Index: 1159277 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.9819. Min Act: -0.1700
Data Index: 8605677 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.9507. Min Act: -0.1700
Data Index: 7931210 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.9194. Min Act: -0.1700
Data Index: 843582 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.8569. Min Act: -0.1700
Data Index: 1845626 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.8569. Min Act: -0.1700
Data Index: 6313350 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.7944. Min Act: -0.1700
Data Index: 1408304 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.7944. Min Act: -0.1700
Data Index: 4466146 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.7632. Min Act: -0.1700
Data Index: 4429764 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.7632. Min Act: -0.1700
Data Index: 6810065 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.7319. Min Act: -0.1700
Data Index: 4672864 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.7007. Min Act: -0.1700
Data Index: 5856753 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.7007. Min Act: -0.1700
Data Index: 407542 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.6694. Min Act: -0.1700
Data Index: 2759065 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.6694. Min Act: -0.1700
Data Index: 7370050 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.6382. Min Act: -0.1700
Data Index: 4474607 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.6382. Min Act: -0.1700
Data Index: 2286904 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.6069. Min Act: -0.1700
Data Index: 96989 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1069. Min Range: -6.1069
Max Act: 5.6382. Min Act: -0.1700
Data Index: 6230515 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19