Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2760 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0672. Min Range: -5.0672
Max Act: 5.0672. Min Act: -0.1700
Data Index: 7791591 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.8797. Min Act: -0.1700
Data Index: 7367354 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.8484. Min Act: -0.1700
Data Index: 2696001 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.8172. Min Act: -0.1700
Data Index: 391324 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.8484. Min Act: -0.1700
Data Index: 1196926 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.7859. Min Act: -0.1700
Data Index: 2872172 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.7859. Min Act: -0.1700
Data Index: 8150335 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.8172. Min Act: -0.1700
Data Index: 4503546 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.7547. Min Act: -0.1700
Data Index: 99637 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.7547. Min Act: -0.1700
Data Index: 1892675 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.8172. Min Act: -0.1700
Data Index: 99639 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.7234. Min Act: -0.1700
Data Index: 3080130 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.7234. Min Act: -0.1700
Data Index: 5670103 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.7234. Min Act: -0.1700
Data Index: 8034584 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.6922. Min Act: -0.1700
Data Index: 7367368 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.7234. Min Act: -0.1700
Data Index: 8150336 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.6922. Min Act: -0.1700
Data Index: 2292717 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.6922. Min Act: -0.1700
Data Index: 1986668 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.6609. Min Act: -0.1700
Data Index: 6018982 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0672. Min Range: -5.0672
Max Act: 4.6922. Min Act: -0.1700
Data Index: 5791703 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19