Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2191 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.5083. Min Act: -0.1700
Data Index: 208987 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.3521. Min Act: -0.1700
Data Index: 464351 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.3521. Min Act: -0.1700
Data Index: 1691749 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.2896. Min Act: -0.1700
Data Index: 8764230 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.2583. Min Act: -0.1700
Data Index: 3160510 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.2271. Min Act: -0.1700
Data Index: 3165201 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.2271. Min Act: -0.1700
Data Index: 578913 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.2271. Min Act: -0.1700
Data Index: 3281329 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1958. Min Act: -0.1700
Data Index: 5627644 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.2271. Min Act: -0.1700
Data Index: 327935 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1958. Min Act: -0.1700
Data Index: 1228640 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1646. Min Act: -0.1700
Data Index: 2363032 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1646. Min Act: -0.1700
Data Index: 7721240 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1958. Min Act: -0.1700
Data Index: 3995571 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1958. Min Act: -0.1700
Data Index: 5889154 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1646. Min Act: -0.1700
Data Index: 144151 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1646. Min Act: -0.1700
Data Index: 5854803 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1333. Min Act: -0.1700
Data Index: 5142132 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1646. Min Act: -0.1700
Data Index: 7367934 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5083. Min Range: -4.5083
Max Act: 4.1646. Min Act: -0.1700
Data Index: 8506786 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19