Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3274 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.2646. Min Act: -0.1700
Data Index: 3228803 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.2334. Min Act: -0.1700
Data Index: 5794337 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.2021. Min Act: -0.1700
Data Index: 4917535 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.1709. Min Act: -0.1700
Data Index: 2784217 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.1396. Min Act: -0.1700
Data Index: 4179024 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.1396. Min Act: -0.1700
Data Index: 3743014 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.1396. Min Act: -0.1700
Data Index: 8160746 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.1084. Min Act: -0.1700
Data Index: 6771651 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.1084. Min Act: -0.1700
Data Index: 2406642 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.1084. Min Act: -0.1700
Data Index: 3577371 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.1084. Min Act: -0.1700
Data Index: 5859833 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.0771. Min Act: -0.1700
Data Index: 2502769 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.0771. Min Act: -0.1700
Data Index: 131682 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.0459. Min Act: -0.1700
Data Index: 5026682 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.0771. Min Act: -0.1700
Data Index: 2025240 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.0771. Min Act: -0.1700
Data Index: 8229587 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.0771. Min Act: -0.1700
Data Index: 8390944 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.0771. Min Act: -0.1700
Data Index: 6936483 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.0771. Min Act: -0.1700
Data Index: 7401715 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2646. Min Range: -6.2646
Max Act: 6.0459. Min Act: -0.1700
Data Index: 6858447 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19