Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 832 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4240. Min Range: -8.4240
Max Act: 8.4240. Min Act: -0.1700
Data Index: 3567896 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4240. Min Range: -8.4240
Max Act: 8.1115. Min Act: -0.1700
Data Index: 4576524 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4240. Min Range: -8.4240
Max Act: 8.0490. Min Act: -0.1700
Data Index: 6890665 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.9865. Min Act: -0.1700
Data Index: 1706456 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.9865. Min Act: -0.1700
Data Index: 5733568 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.8615. Min Act: -0.1700
Data Index: 7891305 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.8615. Min Act: -0.1700
Data Index: 1315963 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.8302. Min Act: -0.1700
Data Index: 2499027 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.7677. Min Act: -0.1700
Data Index: 3457255 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.7677. Min Act: -0.1700
Data Index: 1383121 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.8302. Min Act: -0.1700
Data Index: 1362756 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.7052. Min Act: -0.1700
Data Index: 1315962 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.7365. Min Act: -0.1700
Data Index: 8131145 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.6740. Min Act: -0.1700
Data Index: 1269298 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.6427. Min Act: -0.1700
Data Index: 8115610 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.5177. Min Act: -0.1700
Data Index: 2854920 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.5802. Min Act: -0.1700
Data Index: 7403239 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.5177. Min Act: -0.1700
Data Index: 1315964 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.5177. Min Act: -0.1700
Data Index: 846941 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4240. Min Range: -8.4240
Max Act: 7.6115. Min Act: -0.1700
Data Index: 5741004 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19