Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 259 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3824. Min Range: -6.3824
Max Act: 6.3824. Min Act: -0.1700
Data Index: 8646123 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.8511. Min Act: -0.1700
Data Index: 6372157 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.8511. Min Act: -0.1700
Data Index: 1866586 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.7886. Min Act: -0.1700
Data Index: 4914187 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.8199. Min Act: -0.1700
Data Index: 4457233 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.7574. Min Act: -0.1700
Data Index: 2792283 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.7574. Min Act: -0.1700
Data Index: 509652 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.6949. Min Act: -0.1700
Data Index: 2770357 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.6949. Min Act: -0.1700
Data Index: 5086040 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.6636. Min Act: -0.1700
Data Index: 2467713 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.6324. Min Act: -0.1700
Data Index: 4914188 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.6324. Min Act: -0.1700
Data Index: 8351573 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.6011. Min Act: -0.1700
Data Index: 4457234 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.6011. Min Act: -0.1700
Data Index: 1556865 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.6011. Min Act: -0.1700
Data Index: 4163996 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.6324. Min Act: -0.1700
Data Index: 737637 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.5699. Min Act: -0.1700
Data Index: 1612907 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.5699. Min Act: -0.1700
Data Index: 8238448 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.5699. Min Act: -0.1700
Data Index: 7828376 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3824. Min Range: -6.3824
Max Act: 5.5699. Min Act: -0.1700
Data Index: 6673131 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19