Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0956. Min Range: -5.0956
Max Act: 5.0956. Min Act: -0.1700
Data Index: 308295 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0956. Min Range: -5.0956
Max Act: 5.0331. Min Act: -0.1700
Data Index: 2529146 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9393. Min Act: -0.1700
Data Index: 110554 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9393. Min Act: -0.1700
Data Index: 1146373 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9393. Min Act: -0.1700
Data Index: 5293594 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9393. Min Act: -0.1700
Data Index: 328230 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9081. Min Act: -0.1700
Data Index: 1972950 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9393. Min Act: -0.1700
Data Index: 8227341 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9081. Min Act: -0.1700
Data Index: 989216 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9081. Min Act: -0.1700
Data Index: 2956665 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9081. Min Act: -0.1700
Data Index: 2734170 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9081. Min Act: -0.1700
Data Index: 8472446 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9081. Min Act: -0.1700
Data Index: 7549334 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.8768. Min Act: -0.1700
Data Index: 6914869 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9081. Min Act: -0.1700
Data Index: 4208540 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9081. Min Act: -0.1700
Data Index: 6606567 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.8768. Min Act: -0.1700
Data Index: 6425637 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9081. Min Act: -0.1700
Data Index: 6226100 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.9081. Min Act: -0.1700
Data Index: 4340803 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0956. Min Range: -5.0956
Max Act: 4.8768. Min Act: -0.1700
Data Index: 2886735 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19