Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0160. Min Range: -7.0160
Max Act: 7.0160. Min Act: -0.1700
Data Index: 8729250 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.9535. Min Act: -0.1700
Data Index: 3679209 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.7035. Min Act: -0.1700
Data Index: 1493014 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.6410. Min Act: -0.1700
Data Index: 8181813 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.5785. Min Act: -0.1700
Data Index: 5220360 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.5472. Min Act: -0.1700
Data Index: 3122808 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.5472. Min Act: -0.1700
Data Index: 7946081 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.4535. Min Act: -0.1700
Data Index: 855560 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.4535. Min Act: -0.1700
Data Index: 8055028 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.4535. Min Act: -0.1700
Data Index: 2963251 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.4847. Min Act: -0.1700
Data Index: 3143684 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.4222. Min Act: -0.1700
Data Index: 6110650 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.4222. Min Act: -0.1700
Data Index: 8459142 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.3597. Min Act: -0.1700
Data Index: 3301922 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.4535. Min Act: -0.1700
Data Index: 359330 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.4222. Min Act: -0.1700
Data Index: 598864 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.3285. Min Act: -0.1700
Data Index: 2549409 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.3285. Min Act: -0.1700
Data Index: 358928 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.2660. Min Act: -0.1700
Data Index: 7004021 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0160. Min Range: -7.0160
Max Act: 6.2660. Min Act: -0.1700
Data Index: 6327324 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19