Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2765 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.3617. Min Act: -0.1700
Data Index: 1165509 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.3929. Min Act: -0.1700
Data Index: 5666757 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.3304. Min Act: -0.1700
Data Index: 2853387 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.3617. Min Act: -0.1700
Data Index: 1938955 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.3304. Min Act: -0.1700
Data Index: 4309565 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.3304. Min Act: -0.1700
Data Index: 5970211 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.2054. Min Act: -0.1700
Data Index: 7154262 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.2054. Min Act: -0.1700
Data Index: 2013128 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.2679. Min Act: -0.1700
Data Index: 7940017 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.2679. Min Act: -0.1700
Data Index: 1643249 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.2054. Min Act: -0.1700
Data Index: 647604 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.1742. Min Act: -0.1700
Data Index: 4826869 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.1742. Min Act: -0.1700
Data Index: 338035 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.1429. Min Act: -0.1700
Data Index: 6157138 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.1117. Min Act: -0.1700
Data Index: 1044602 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.1429. Min Act: -0.1700
Data Index: 323260 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.0492. Min Act: -0.1699
Data Index: 1073311 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.0804. Min Act: -0.1700
Data Index: 969516 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.0804. Min Act: -0.1700
Data Index: 710020 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3929. Min Range: -6.3929
Max Act: 6.1117. Min Act: -0.1700
Data Index: 2201311 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19