Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.5613. Min Act: -0.1700
Data Index: 3452869 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.5300. Min Act: -0.1700
Data Index: 753811 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.4363. Min Act: -0.1700
Data Index: 6407084 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.3738. Min Act: -0.1700
Data Index: 6724711 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.3425. Min Act: -0.1700
Data Index: 3452870 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.3425. Min Act: -0.1700
Data Index: 772424 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.3425. Min Act: -0.1700
Data Index: 6363247 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.2488. Min Act: -0.1700
Data Index: 1973117 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.2800. Min Act: -0.1700
Data Index: 4499600 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.2800. Min Act: -0.1700
Data Index: 6407085 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.2488. Min Act: -0.1700
Data Index: 5627768 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.2175. Min Act: -0.1700
Data Index: 8751856 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5613. Min Range: -5.5613
Max Act: 4.7175. Min Act: -0.1700
Data Index: 1004484 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5613. Min Range: -5.5613
Max Act: 4.6238. Min Act: -0.1700
Data Index: 8422389 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5613. Min Range: -5.5613
Max Act: 4.5300. Min Act: -0.1700
Data Index: 1947979 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5613. Min Range: -5.5613
Max Act: 4.4988. Min Act: -0.1700
Data Index: 8427729 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5613. Min Range: -5.5613
Max Act: 4.4675. Min Act: -0.1700
Data Index: 1117517 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5613. Min Range: -5.5613
Max Act: 4.4363. Min Act: -0.1700
Data Index: 3232768 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5613. Min Range: -5.5613
Max Act: 4.4363. Min Act: -0.1700
Data Index: 5330275 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5613. Min Range: -5.5613
Max Act: 4.4363. Min Act: -0.1700
Data Index: 7247712 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19