Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2487 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.7092. Min Act: -0.1700
Data Index: 6904822 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.3654. Min Act: -0.1700
Data Index: 5926231 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.3342. Min Act: -0.1700
Data Index: 293115 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.3029. Min Act: -0.1700
Data Index: 2438421 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.3029. Min Act: -0.1700
Data Index: 5265839 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.2404. Min Act: -0.1700
Data Index: 4309796 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.2092. Min Act: -0.1700
Data Index: 5058470 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.2717. Min Act: -0.1700
Data Index: 4374080 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.2404. Min Act: -0.1700
Data Index: 1424723 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.2404. Min Act: -0.1700
Data Index: 815623 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.2717. Min Act: -0.1700
Data Index: 3007408 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.2092. Min Act: -0.1700
Data Index: 5988053 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.1779. Min Act: -0.1700
Data Index: 1410503 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.1779. Min Act: -0.1700
Data Index: 1325141 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.1779. Min Act: -0.1700
Data Index: 7373219 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.1779. Min Act: -0.1700
Data Index: 456548 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.1779. Min Act: -0.1700
Data Index: 6513770 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.1779. Min Act: -0.1700
Data Index: 8119652 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.1779. Min Act: -0.1700
Data Index: 49091 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7092. Min Range: -7.7092
Max Act: 7.1154. Min Act: -0.1700
Data Index: 4001182 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19