Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6188 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.4468. Min Act: -0.1700
Data Index: 1252643 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.3530. Min Act: -0.1700
Data Index: 1579021 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.1968. Min Act: -0.1700
Data Index: 7393053 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.1343. Min Act: -0.1700
Data Index: 2987620 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.1030. Min Act: -0.1700
Data Index: 2392881 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.1030. Min Act: -0.1700
Data Index: 3485934 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.0405. Min Act: -0.1700
Data Index: 6017419 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.0405. Min Act: -0.1700
Data Index: 7091643 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.0093. Min Act: -0.1700
Data Index: 5173486 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.0093. Min Act: -0.1700
Data Index: 2485267 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.9468. Min Act: -0.1700
Data Index: 2806485 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.9468. Min Act: -0.1700
Data Index: 4646090 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.9155. Min Act: -0.1700
Data Index: 7758987 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.9155. Min Act: -0.1700
Data Index: 2477016 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.8843. Min Act: -0.1700
Data Index: 1372308 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.8843. Min Act: -0.1700
Data Index: 926524 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.8530. Min Act: -0.1700
Data Index: 2225679 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.8843. Min Act: -0.1700
Data Index: 4825520 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.8530. Min Act: -0.1700
Data Index: 1446538 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.8530. Min Act: -0.1700
Data Index: 738171 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19