Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1557 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1026. Min Range: -7.1026
Max Act: 7.1026. Min Act: -0.1700
Data Index: 1522927 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1026. Min Range: -7.1026
Max Act: 7.0401. Min Act: -0.1700
Data Index: 403793 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.7589. Min Act: -0.1700
Data Index: 772367 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.6964. Min Act: -0.1700
Data Index: 86476 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.7276. Min Act: -0.1700
Data Index: 4490633 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.7276. Min Act: -0.1700
Data Index: 7204394 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.6964. Min Act: -0.1700
Data Index: 8632812 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.6964. Min Act: -0.1700
Data Index: 4951896 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.6651. Min Act: -0.1700
Data Index: 6099800 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.6651. Min Act: -0.1700
Data Index: 171409 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.6339. Min Act: -0.1700
Data Index: 8431781 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.6026. Min Act: -0.1700
Data Index: 2659154 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.6026. Min Act: -0.1700
Data Index: 783279 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.6026. Min Act: -0.1700
Data Index: 4522294 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.6026. Min Act: -0.1700
Data Index: 4672621 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.5714. Min Act: -0.1700
Data Index: 5323128 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.5401. Min Act: -0.1700
Data Index: 7916313 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.5401. Min Act: -0.1700
Data Index: 4507686 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.5714. Min Act: -0.1700
Data Index: 1900293 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1026. Min Range: -7.1026
Max Act: 6.5401. Min Act: -0.1700
Data Index: 6531343 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19