Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3010 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7575. Min Act: -0.1700
Data Index: 1136701 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7489. Min Act: -0.1700
Data Index: 2183602 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7403. Min Act: -0.1700
Data Index: 2327581 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7316. Min Act: -0.1700
Data Index: 8603333 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7316. Min Act: -0.1700
Data Index: 5687060 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7056. Min Act: -0.1699
Data Index: 3106811 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7230. Min Act: -0.1700
Data Index: 5827773 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7056. Min Act: -0.1700
Data Index: 3944455 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7143. Min Act: -0.1700
Data Index: 6361617 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7143. Min Act: -0.1700
Data Index: 707722 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7056. Min Act: -0.1698
Data Index: 8369341 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7056. Min Act: -0.1698
Data Index: 5799938 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.6970. Min Act: -0.1700
Data Index: 8333513 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.6970. Min Act: -0.1700
Data Index: 2482197 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7056. Min Act: -0.1699
Data Index: 7724534 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.7056. Min Act: -0.1700
Data Index: 2443924 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.6883. Min Act: -0.1694
Data Index: 8377971 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.6970. Min Act: -0.1700
Data Index: 4812942 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.6970. Min Act: -0.1700
Data Index: 4443248 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7575. Min Range: -1.7575
Max Act: 1.6883. Min Act: -0.1700
Data Index: 4825379 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19