Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.7208. Min Act: -0.1700
Data Index: 7104174 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.3771. Min Act: -0.1700
Data Index: 1003930 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.4083. Min Act: -0.1700
Data Index: 3213731 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.3771. Min Act: -0.1700
Data Index: 437556 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.2833. Min Act: -0.1700
Data Index: 6237823 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.2521. Min Act: -0.1700
Data Index: 2684821 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.2521. Min Act: -0.1700
Data Index: 7989089 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.2208. Min Act: -0.1700
Data Index: 2956929 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.3146. Min Act: -0.1700
Data Index: 2675757 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.2208. Min Act: -0.1700
Data Index: 5405318 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.1896. Min Act: -0.1700
Data Index: 224057 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.1583. Min Act: -0.1700
Data Index: 6680736 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.2208. Min Act: -0.1700
Data Index: 6593538 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.1583. Min Act: -0.1700
Data Index: 6380536 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.1271. Min Act: -0.1700
Data Index: 3120175 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.0646. Min Act: -0.1700
Data Index: 1635715 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.1271. Min Act: -0.1700
Data Index: 498304 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.0958. Min Act: -0.1700
Data Index: 7625747 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.0958. Min Act: -0.1700
Data Index: 5119439 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7208. Min Range: -5.7208
Max Act: 5.0646. Min Act: -0.1700
Data Index: 1074264 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19