Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3175 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.6303. Min Act: -0.1700
Data Index: 2784259 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.3803. Min Act: -0.1700
Data Index: 5449060 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.3490. Min Act: -0.1700
Data Index: 8583420 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.2553. Min Act: -0.1700
Data Index: 4992230 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.2553. Min Act: -0.1700
Data Index: 4115253 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.2553. Min Act: -0.1700
Data Index: 1408173 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.2240. Min Act: -0.1700
Data Index: 4992232 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.2240. Min Act: -0.1700
Data Index: 8104278 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.2240. Min Act: -0.1700
Data Index: 4992231 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.1615. Min Act: -0.1700
Data Index: 4722143 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.1615. Min Act: -0.1700
Data Index: 4899460 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.1615. Min Act: -0.1700
Data Index: 4387141 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.1615. Min Act: -0.1700
Data Index: 6260856 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.1615. Min Act: -0.1700
Data Index: 5447093 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.1615. Min Act: -0.1700
Data Index: 8005579 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.1303. Min Act: -0.1700
Data Index: 7285143 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.1303. Min Act: -0.1700
Data Index: 8790172 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.1303. Min Act: -0.1700
Data Index: 2907257 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.1303. Min Act: -0.1700
Data Index: 7777872 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6303. Min Range: -4.6303
Max Act: 4.0990. Min Act: -0.1700
Data Index: 6260857 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19