Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1926 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.8835. Min Act: -0.1700
Data Index: 367869 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.8664. Min Act: -0.1700
Data Index: 1819893 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.8321. Min Act: -0.1700
Data Index: 8681852 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.8493. Min Act: -0.1700
Data Index: 3673988 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.8493. Min Act: -0.1700
Data Index: 8329734 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.8150. Min Act: -0.1700
Data Index: 4852242 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7978. Min Act: -0.1700
Data Index: 1548745 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7805. Min Act: -0.1700
Data Index: 5678835 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.8150. Min Act: -0.1700
Data Index: 8143720 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7978. Min Act: -0.1698
Data Index: 7876624 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7978. Min Act: -0.1700
Data Index: 7541026 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7805. Min Act: -0.1700
Data Index: 5779309 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7633. Min Act: -0.1700
Data Index: 8480146 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7633. Min Act: -0.1700
Data Index: 1731469 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7633. Min Act: -0.1700
Data Index: 7555225 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7633. Min Act: -0.1700
Data Index: 6557487 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7633. Min Act: -0.1700
Data Index: 1655153 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7374. Min Act: -0.1700
Data Index: 2771389 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7460. Min Act: -0.1700
Data Index: 233720 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8835. Min Range: -1.8835
Max Act: 1.7374. Min Act: -0.1700
Data Index: 6464811 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19