Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2830 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.6964. Min Act: -0.1700
Data Index: 6913938 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.6338. Min Act: -0.1700
Data Index: 7184783 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.5869. Min Act: -0.1700
Data Index: 3624714 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.5556. Min Act: -0.1700
Data Index: 5175030 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.4773. Min Act: -0.1700
Data Index: 1152524 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.4303. Min Act: -0.1700
Data Index: 449367 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.4303. Min Act: -0.1700
Data Index: 28918 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.4303. Min Act: -0.1700
Data Index: 2319155 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.4146. Min Act: -0.1700
Data Index: 4949252 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.4459. Min Act: -0.1700
Data Index: 669846 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.3989. Min Act: -0.1700
Data Index: 2604989 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.3832. Min Act: -0.1700
Data Index: 3728929 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.4146. Min Act: -0.1700
Data Index: 745266 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.3832. Min Act: -0.1700
Data Index: 5154062 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.3989. Min Act: -0.1700
Data Index: 4148290 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.3675. Min Act: -0.1700
Data Index: 5640335 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.3675. Min Act: -0.1700
Data Index: 988951 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.3675. Min Act: -0.1700
Data Index: 690957 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.3832. Min Act: -0.1700
Data Index: 8274719 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6964. Min Range: -3.6964
Max Act: 3.3519. Min Act: -0.1700
Data Index: 4113436 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19