Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 555 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5700. Min Act: -0.1700
Data Index: 2652414 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5700. Min Act: -0.1700
Data Index: 3595989 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5387. Min Act: -0.1700
Data Index: 2582655 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5387. Min Act: -0.1700
Data Index: 1975817 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 211578 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 8163305 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 1831334 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 6831806 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 6719434 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 1756287 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5387. Min Act: -0.1700
Data Index: 6512656 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 6257239 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.4761. Min Act: -0.1700
Data Index: 1397901 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 5664631 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 5307081 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 4323510 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 1022674 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 3602871 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 3318465 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5700. Min Range: -3.5700
Max Act: 3.5074. Min Act: -0.1700
Data Index: 3230671 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19