Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4948 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2258. Min Range: -9.2258
Max Act: 9.2258. Min Act: -0.1700
Data Index: 193551 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2258. Min Range: -9.2258
Max Act: 9.1008. Min Act: -0.1700
Data Index: 7428115 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2258. Min Range: -9.2258
Max Act: 9.1008. Min Act: -0.1700
Data Index: 6396016 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.9758. Min Act: -0.1700
Data Index: 6330465 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.9133. Min Act: -0.1700
Data Index: 4297532 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.7258. Min Act: -0.1700
Data Index: 2777028 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.6633. Min Act: -0.1700
Data Index: 3480421 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.6633. Min Act: -0.1700
Data Index: 8136407 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.6008. Min Act: -0.1700
Data Index: 3437890 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.6633. Min Act: -0.1700
Data Index: 6002076 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.6008. Min Act: -0.1700
Data Index: 8303390 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.6008. Min Act: -0.1700
Data Index: 629753 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.5383. Min Act: -0.1700
Data Index: 8281865 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.4758. Min Act: -0.1700
Data Index: 5160077 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.4758. Min Act: -0.1700
Data Index: 7557591 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.4758. Min Act: -0.1700
Data Index: 2959531 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.4758. Min Act: -0.1700
Data Index: 5038869 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.4758. Min Act: -0.1700
Data Index: 59642 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.3508. Min Act: -0.1700
Data Index: 4297531 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2258. Min Range: -9.2258
Max Act: 8.4133. Min Act: -0.1700
Data Index: 7000265 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19