Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3340 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.4554. Min Act: -0.1700
Data Index: 8307851 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.4066. Min Act: -0.1700
Data Index: 736837 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.3247. Min Act: -0.1700
Data Index: 5991059 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.3083. Min Act: -0.1700
Data Index: 6444930 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.3083. Min Act: -0.1700
Data Index: 627086 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.3412. Min Act: -0.1700
Data Index: 1091800 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.3083. Min Act: -0.1700
Data Index: 283863 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.3083. Min Act: -0.1700
Data Index: 5694331 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.3083. Min Act: -0.1700
Data Index: 4046231 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.3083. Min Act: -0.1700
Data Index: 1297633 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.2919. Min Act: -0.1700
Data Index: 3317007 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.2589. Min Act: -0.1700
Data Index: 3755715 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.2589. Min Act: -0.1700
Data Index: 1439632 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.2589. Min Act: -0.1700
Data Index: 5597371 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.2424. Min Act: -0.1700
Data Index: 1255777 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.2424. Min Act: -0.1700
Data Index: 3925433 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.2258. Min Act: -0.1700
Data Index: 2851383 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.2258. Min Act: -0.1700
Data Index: 7779720 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.2424. Min Act: -0.1700
Data Index: 1811904 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4554. Min Range: -2.4554
Max Act: 2.2589. Min Act: -0.1700
Data Index: 5603039 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19