Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1097 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0479. Min Range: -5.0479
Max Act: 5.0479. Min Act: -0.1700
Data Index: 1726977 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0479. Min Range: -5.0479
Max Act: 5.0166. Min Act: -0.1700
Data Index: 8157907 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0479. Min Range: -5.0479
Max Act: 5.0166. Min Act: -0.1700
Data Index: 6000297 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.9854. Min Act: -0.1700
Data Index: 1043635 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.9541. Min Act: -0.1700
Data Index: 4728890 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.9541. Min Act: -0.1700
Data Index: 5659942 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.9229. Min Act: -0.1700
Data Index: 7500294 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.9229. Min Act: -0.1700
Data Index: 6808528 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.9229. Min Act: -0.1700
Data Index: 2243139 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.9229. Min Act: -0.1700
Data Index: 1057517 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.9229. Min Act: -0.1700
Data Index: 3461240 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.9541. Min Act: -0.1700
Data Index: 1450080 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.8604. Min Act: -0.1700
Data Index: 3547321 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.8916. Min Act: -0.1700
Data Index: 1571536 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.8916. Min Act: -0.1700
Data Index: 1400297 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.8916. Min Act: -0.1700
Data Index: 5873973 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.8604. Min Act: -0.1700
Data Index: 2580636 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.8916. Min Act: -0.1700
Data Index: 5403092 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.8604. Min Act: -0.1700
Data Index: 5067129 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0479. Min Range: -5.0479
Max Act: 4.8916. Min Act: -0.1700
Data Index: 4538100 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19