Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0543. Min Range: -6.0543
Max Act: 6.0543. Min Act: -0.1700
Data Index: 5239033 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0543. Min Range: -6.0543
Max Act: 6.0231. Min Act: -0.1700
Data Index: 7886697 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.9918. Min Act: -0.1700
Data Index: 3999840 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.9606. Min Act: -0.1700
Data Index: 2297316 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8981. Min Act: -0.1700
Data Index: 2711460 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8668. Min Act: -0.1700
Data Index: 7704783 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8668. Min Act: -0.1700
Data Index: 6212160 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8668. Min Act: -0.1700
Data Index: 4088377 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8668. Min Act: -0.1700
Data Index: 4834081 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8356. Min Act: -0.1700
Data Index: 3550886 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8356. Min Act: -0.1700
Data Index: 1696393 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8356. Min Act: -0.1700
Data Index: 3351855 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8043. Min Act: -0.1700
Data Index: 2994116 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8356. Min Act: -0.1700
Data Index: 614926 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8356. Min Act: -0.1700
Data Index: 8798539 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8356. Min Act: -0.1700
Data Index: 2337844 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8043. Min Act: -0.1700
Data Index: 2210515 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8356. Min Act: -0.1700
Data Index: 6443740 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8043. Min Act: -0.1700
Data Index: 443582 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0543. Min Range: -6.0543
Max Act: 5.8043. Min Act: -0.1700
Data Index: 417460 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19