Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1817 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0443. Min Range: -7.0443
Max Act: 7.0443. Min Act: -0.1700
Data Index: 1803283 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.7006. Min Act: -0.1700
Data Index: 4962942 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.6693. Min Act: -0.1700
Data Index: 45381 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.6693. Min Act: -0.1700
Data Index: 5279230 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.6693. Min Act: -0.1700
Data Index: 1004334 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.6693. Min Act: -0.1700
Data Index: 3127652 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.6068. Min Act: -0.1700
Data Index: 7230225 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.6068. Min Act: -0.1700
Data Index: 541248 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.6068. Min Act: -0.1700
Data Index: 30358 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.5443. Min Act: -0.1700
Data Index: 3746230 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.5131. Min Act: -0.1700
Data Index: 2668346 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.5756. Min Act: -0.1700
Data Index: 1908553 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.5756. Min Act: -0.1700
Data Index: 5436375 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.5131. Min Act: -0.1700
Data Index: 5442477 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.4818. Min Act: -0.1700
Data Index: 8270078 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.4818. Min Act: -0.1700
Data Index: 5353368 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.5131. Min Act: -0.1700
Data Index: 6319838 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.4818. Min Act: -0.1700
Data Index: 2769525 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.4818. Min Act: -0.1700
Data Index: 5641263 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0443. Min Range: -7.0443
Max Act: 6.4818. Min Act: -0.1700
Data Index: 2248057 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19