Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0981. Min Range: -9.0981
Max Act: 9.0981. Min Act: -0.1700
Data Index: 8235314 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0981. Min Range: -9.0981
Max Act: 9.0356. Min Act: -0.1700
Data Index: 6099251 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.7231. Min Act: -0.1700
Data Index: 1621611 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.6606. Min Act: -0.1700
Data Index: 576829 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.5981. Min Act: -0.1700
Data Index: 3152242 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.5356. Min Act: -0.1700
Data Index: 2951898 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.5356. Min Act: -0.1700
Data Index: 69033 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.5356. Min Act: -0.1700
Data Index: 2425901 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.4731. Min Act: -0.1700
Data Index: 6714247 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.4731. Min Act: -0.1700
Data Index: 3477615 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.4731. Min Act: -0.1700
Data Index: 6276729 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.4731. Min Act: -0.1700
Data Index: 7652174 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.4731. Min Act: -0.1700
Data Index: 2447789 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.4106. Min Act: -0.1700
Data Index: 5026565 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.4106. Min Act: -0.1700
Data Index: 5206355 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.4106. Min Act: -0.1700
Data Index: 5180176 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.4106. Min Act: -0.1700
Data Index: 7775290 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.4106. Min Act: -0.1700
Data Index: 5493953 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.3481. Min Act: -0.1700
Data Index: 160821 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0981. Min Range: -9.0981
Max Act: 8.3481. Min Act: -0.1700
Data Index: 2491924 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19