Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1192 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.6070. Min Act: -0.1700
Data Index: 6932909 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.5288. Min Act: -0.1700
Data Index: 2000961 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.4818. Min Act: -0.1700
Data Index: 5678971 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.4504. Min Act: -0.1700
Data Index: 5201068 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.4504. Min Act: -0.1700
Data Index: 8039379 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.3877. Min Act: -0.1700
Data Index: 2630295 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.4034. Min Act: -0.1700
Data Index: 3236770 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.3721. Min Act: -0.1700
Data Index: 6932914 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.3250. Min Act: -0.1700
Data Index: 5192918 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.3564. Min Act: -0.1700
Data Index: 374811 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.3407. Min Act: -0.1700
Data Index: 3400600 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.3250. Min Act: -0.1700
Data Index: 3814165 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.3250. Min Act: -0.1700
Data Index: 4905774 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.3250. Min Act: -0.1700
Data Index: 8032585 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.3250. Min Act: -0.1700
Data Index: 8077131 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.2936. Min Act: -0.1700
Data Index: 7097108 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.2936. Min Act: -0.1700
Data Index: 5845263 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.2936. Min Act: -0.1700
Data Index: 5956190 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.2936. Min Act: -0.1700
Data Index: 946647 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6070. Min Range: -3.6070
Max Act: 3.2779. Min Act: -0.1700
Data Index: 6426314 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19