Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8005. Min Range: -6.8005
Max Act: 6.8005. Min Act: -0.1700
Data Index: 8198144 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8005. Min Range: -6.8005
Max Act: 6.3943. Min Act: -0.1700
Data Index: 8490221 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8005. Min Range: -6.8005
Max Act: 6.3318. Min Act: -0.1700
Data Index: 345592 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8005. Min Range: -6.8005
Max Act: 6.2068. Min Act: -0.1700
Data Index: 7806209 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8005. Min Range: -6.8005
Max Act: 6.1755. Min Act: -0.1700
Data Index: 6868807 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8005. Min Range: -6.8005
Max Act: 6.0505. Min Act: -0.1700
Data Index: 7463011 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8005. Min Range: -6.8005
Max Act: 6.0193. Min Act: -0.1700
Data Index: 1416646 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8005. Min Range: -6.8005
Max Act: 6.0193. Min Act: -0.1700
Data Index: 5230992 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8005. Min Range: -6.8005
Max Act: 6.0193. Min Act: -0.1700
Data Index: 2966552 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.9568. Min Act: -0.1700
Data Index: 7288224 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.9255. Min Act: -0.1700
Data Index: 4891207 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.8630. Min Act: -0.1700
Data Index: 6963023 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.9255. Min Act: -0.1700
Data Index: 4174083 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.9255. Min Act: -0.1700
Data Index: 322043 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.8943. Min Act: -0.1700
Data Index: 8714791 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.8943. Min Act: -0.1700
Data Index: 588901 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.8943. Min Act: -0.1700
Data Index: 6747664 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.8630. Min Act: -0.1700
Data Index: 6603152 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.8318. Min Act: -0.1700
Data Index: 6026119 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8005. Min Range: -6.8005
Max Act: 5.8318. Min Act: -0.1700
Data Index: 1352436 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19