Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4965 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.2159. Min Act: -0.1700
Data Index: 4719 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1993. Min Act: -0.1700
Data Index: 7609598 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1827. Min Act: -0.1700
Data Index: 7609597 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1327. Min Act: -0.1700
Data Index: 8248462 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1327. Min Act: -0.1700
Data Index: 2128940 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1661. Min Act: -0.1700
Data Index: 2855802 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1494. Min Act: -0.1700
Data Index: 144898 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1327. Min Act: -0.1700
Data Index: 8030995 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1327. Min Act: -0.1700
Data Index: 3626830 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1160. Min Act: -0.1700
Data Index: 1252607 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1494. Min Act: -0.1700
Data Index: 6234496 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1160. Min Act: -0.1700
Data Index: 32960 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1160. Min Act: -0.1700
Data Index: 737905 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1160. Min Act: -0.1700
Data Index: 5806325 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1160. Min Act: -0.1700
Data Index: 5291998 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.0993. Min Act: -0.1700
Data Index: 3651750 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.1327. Min Act: -0.1700
Data Index: 8412094 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.0993. Min Act: -0.1700
Data Index: 7552331 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.0993. Min Act: -0.1700
Data Index: 3356424 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2159. Min Range: -2.2159
Max Act: 2.0825. Min Act: -0.1700
Data Index: 4572473 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19