Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3099 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.9916. Min Act: -0.1700
Data Index: 7603606 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.9291. Min Act: -0.1700
Data Index: 7579962 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.8353. Min Act: -0.1700
Data Index: 5026614 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.8041. Min Act: -0.1700
Data Index: 2590302 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.7728. Min Act: -0.1700
Data Index: 8701917 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.6791. Min Act: -0.1700
Data Index: 1261515 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.6478. Min Act: -0.1700
Data Index: 8029021 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.6166. Min Act: -0.1700
Data Index: 577327 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.6166. Min Act: -0.1700
Data Index: 1922756 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.6166. Min Act: -0.1700
Data Index: 3214546 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.5853. Min Act: -0.1700
Data Index: 4569815 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.6166. Min Act: -0.1700
Data Index: 175678 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.5853. Min Act: -0.1700
Data Index: 3657485 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.5541. Min Act: -0.1700
Data Index: 952610 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.5853. Min Act: -0.1700
Data Index: 8813538 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.5541. Min Act: -0.1700
Data Index: 4045858 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.5228. Min Act: -0.1700
Data Index: 8569913 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.5228. Min Act: -0.1700
Data Index: 5165479 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.5228. Min Act: -0.1700
Data Index: 4039072 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9916. Min Range: -5.9916
Max Act: 5.5228. Min Act: -0.1700
Data Index: 5604474 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19