Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.5964. Min Act: -0.1700
Data Index: 1264506 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.3777. Min Act: -0.1700
Data Index: 3186792 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.3777. Min Act: -0.1700
Data Index: 2600527 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.3777. Min Act: -0.1700
Data Index: 2402362 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.3777. Min Act: -0.1700
Data Index: 146617 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.3464. Min Act: -0.1700
Data Index: 6957776 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.3464. Min Act: -0.1700
Data Index: 4353092 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.3464. Min Act: -0.1700
Data Index: 1300012 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.3777. Min Act: -0.1700
Data Index: 831460 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.3777. Min Act: -0.1700
Data Index: 568464 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.2839. Min Act: -0.1700
Data Index: 289937 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.3152. Min Act: -0.1700
Data Index: 3975544 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.2527. Min Act: -0.1700
Data Index: 4687083 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.2214. Min Act: -0.1700
Data Index: 7153302 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.2527. Min Act: -0.1700
Data Index: 2950550 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.2527. Min Act: -0.1700
Data Index: 743880 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.2527. Min Act: -0.1700
Data Index: 7824639 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.2527. Min Act: -0.1700
Data Index: 3876776 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.2527. Min Act: -0.1700
Data Index: 592002 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5964. Min Range: -4.5964
Max Act: 4.2214. Min Act: -0.1700
Data Index: 2488519 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19