Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 785 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.4916. Min Act: -0.1700
Data Index: 4616462 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.3979. Min Act: -0.1700
Data Index: 431113 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.3354. Min Act: -0.1700
Data Index: 2032986 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.3041. Min Act: -0.1700
Data Index: 737040 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2729. Min Act: -0.1700
Data Index: 6248801 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2729. Min Act: -0.1700
Data Index: 2728331 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2729. Min Act: -0.1700
Data Index: 8124714 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2729. Min Act: -0.1700
Data Index: 7419319 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2729. Min Act: -0.1700
Data Index: 279760 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2416. Min Act: -0.1700
Data Index: 1034188 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2416. Min Act: -0.1700
Data Index: 1730601 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2104. Min Act: -0.1700
Data Index: 1521639 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2104. Min Act: -0.1700
Data Index: 8493933 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2104. Min Act: -0.1700
Data Index: 3903042 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2104. Min Act: -0.1700
Data Index: 3698070 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.1791. Min Act: -0.1700
Data Index: 5215487 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.2104. Min Act: -0.1700
Data Index: 719198 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.1791. Min Act: -0.1700
Data Index: 1125172 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.1791. Min Act: -0.1700
Data Index: 1226183 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4916. Min Range: -6.4916
Max Act: 6.1791. Min Act: -0.1700
Data Index: 3368080 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19