Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.7255. Min Act: -0.1700
Data Index: 669258 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.6630. Min Act: -0.1700
Data Index: 669257 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.5068. Min Act: -0.1700
Data Index: 6039092 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.5068. Min Act: -0.1700
Data Index: 1311650 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.4755. Min Act: -0.1700
Data Index: 645169 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.4443. Min Act: -0.1700
Data Index: 4886440 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.4443. Min Act: -0.1700
Data Index: 5087688 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.3818. Min Act: -0.1700
Data Index: 2422828 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.3818. Min Act: -0.1700
Data Index: 2546262 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.3193. Min Act: -0.1700
Data Index: 3580042 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.3193. Min Act: -0.1700
Data Index: 1619803 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.2880. Min Act: -0.1700
Data Index: 2212918 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.2880. Min Act: -0.1700
Data Index: 7524073 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.2880. Min Act: -0.1700
Data Index: 1585262 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.2880. Min Act: -0.1700
Data Index: 7441440 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.2568. Min Act: -0.1700
Data Index: 147754 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.2880. Min Act: -0.1700
Data Index: 2124043 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.2255. Min Act: -0.1700
Data Index: 1305925 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.1943. Min Act: -0.1700
Data Index: 5239540 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7255. Min Range: -6.7255
Max Act: 6.2255. Min Act: -0.1700
Data Index: 1516063 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19