Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2616 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.6987. Min Act: -0.1700
Data Index: 6601184 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.6987. Min Act: -0.1700
Data Index: 4259650 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.5424. Min Act: -0.1700
Data Index: 3108423 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.5737. Min Act: -0.1700
Data Index: 6699935 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.5424. Min Act: -0.1700
Data Index: 7254998 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.5737. Min Act: -0.1700
Data Index: 6472680 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.5424. Min Act: -0.1700
Data Index: 6658602 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.5112. Min Act: -0.1700
Data Index: 3069309 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.5112. Min Act: -0.1700
Data Index: 1020472 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.5112. Min Act: -0.1700
Data Index: 1258236 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4799. Min Act: -0.1700
Data Index: 7843773 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4799. Min Act: -0.1700
Data Index: 8682729 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4799. Min Act: -0.1700
Data Index: 3733890 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4799. Min Act: -0.1700
Data Index: 4017548 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4799. Min Act: -0.1700
Data Index: 666958 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4487. Min Act: -0.1700
Data Index: 507553 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4487. Min Act: -0.1700
Data Index: 4947218 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4487. Min Act: -0.1700
Data Index: 3564342 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4487. Min Act: -0.1700
Data Index: 7840560 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6987. Min Range: -4.6987
Max Act: 4.4174. Min Act: -0.1700
Data Index: 5735856 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19