Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1368 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1166. Min Range: -5.1166
Max Act: 5.1166. Min Act: -0.1700
Data Index: 5122921 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.9916. Min Act: -0.1700
Data Index: 781449 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.8979. Min Act: -0.1700
Data Index: 6616565 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.8666. Min Act: -0.1700
Data Index: 480861 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.8354. Min Act: -0.1700
Data Index: 5135989 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.8666. Min Act: -0.1700
Data Index: 6709548 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.8354. Min Act: -0.1700
Data Index: 4853654 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7729. Min Act: -0.1700
Data Index: 3799732 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7729. Min Act: -0.1700
Data Index: 6375731 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7729. Min Act: -0.1700
Data Index: 4371202 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7416. Min Act: -0.1700
Data Index: 5141930 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7729. Min Act: -0.1700
Data Index: 4947934 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7416. Min Act: -0.1700
Data Index: 4325420 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7416. Min Act: -0.1700
Data Index: 751254 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7416. Min Act: -0.1700
Data Index: 8543539 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7104. Min Act: -0.1700
Data Index: 3090109 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7104. Min Act: -0.1700
Data Index: 2929882 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7104. Min Act: -0.1700
Data Index: 2154914 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.6791. Min Act: -0.1700
Data Index: 4634204 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1166. Min Range: -5.1166
Max Act: 4.7104. Min Act: -0.1700
Data Index: 5089327 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19