Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 67 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1808. Min Range: -6.1808
Max Act: 6.1808. Min Act: -0.1700
Data Index: 8611478 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1808. Min Range: -6.1808
Max Act: 6.1495. Min Act: -0.1700
Data Index: 8142229 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1808. Min Range: -6.1808
Max Act: 6.0558. Min Act: -0.1700
Data Index: 8611473 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1808. Min Range: -6.1808
Max Act: 6.0870. Min Act: -0.1700
Data Index: 8381167 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.9933. Min Act: -0.1700
Data Index: 4221147 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.9933. Min Act: -0.1700
Data Index: 7800046 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.9933. Min Act: -0.1700
Data Index: 1107122 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.9308. Min Act: -0.1700
Data Index: 8319648 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.9620. Min Act: -0.1700
Data Index: 4151741 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.8995. Min Act: -0.1700
Data Index: 3184839 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.8370. Min Act: -0.1700
Data Index: 493929 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.8370. Min Act: -0.1700
Data Index: 6513569 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.8370. Min Act: -0.1700
Data Index: 8750030 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.8370. Min Act: -0.1700
Data Index: 3368089 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.8058. Min Act: -0.1700
Data Index: 3377345 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.7433. Min Act: -0.1700
Data Index: 4571637 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.7745. Min Act: -0.1700
Data Index: 5629780 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.7433. Min Act: -0.1700
Data Index: 4465704 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.7433. Min Act: -0.1700
Data Index: 4789869 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1808. Min Range: -6.1808
Max Act: 5.7433. Min Act: -0.1700
Data Index: 5397210 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19