Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1089 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0205. Min Range: -3.0205
Max Act: 3.0205. Min Act: -0.1700
Data Index: 2027578 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.8145. Min Act: -0.1700
Data Index: 7224866 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.7826. Min Act: -0.1700
Data Index: 1581219 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.7986. Min Act: -0.1700
Data Index: 3644162 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.7507. Min Act: -0.1700
Data Index: 8657002 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.7188. Min Act: -0.1700
Data Index: 6636160 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.7188. Min Act: -0.1700
Data Index: 802009 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.7188. Min Act: -0.1700
Data Index: 450642 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.7188. Min Act: -0.1700
Data Index: 2303227 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.6708. Min Act: -0.1700
Data Index: 2274456 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.6708. Min Act: -0.1700
Data Index: 6314212 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.6708. Min Act: -0.1700
Data Index: 5784552 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.6547. Min Act: -0.1700
Data Index: 5802878 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.7028. Min Act: -0.1700
Data Index: 3792044 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.6708. Min Act: -0.1700
Data Index: 3888121 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.6708. Min Act: -0.1700
Data Index: 2496980 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.6708. Min Act: -0.1700
Data Index: 6332234 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.6547. Min Act: -0.1700
Data Index: 1656509 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.6226. Min Act: -0.1700
Data Index: 4055637 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0205. Min Range: -3.0205
Max Act: 2.6226. Min Act: -0.1700
Data Index: 2704187 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19