Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1621 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1390. Min Range: -3.1390
Max Act: 3.1390. Min Act: -0.1700
Data Index: 7470126 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9971. Min Act: -0.1700
Data Index: 1394001 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9971. Min Act: -0.1700
Data Index: 1325483 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9496. Min Act: -0.1700
Data Index: 1938095 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9496. Min Act: -0.1700
Data Index: 5216232 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9338. Min Act: -0.1700
Data Index: 6963650 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9338. Min Act: -0.1700
Data Index: 835694 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9338. Min Act: -0.1700
Data Index: 6254868 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9338. Min Act: -0.1699
Data Index: 2265582 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9179. Min Act: -0.1700
Data Index: 359090 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9338. Min Act: -0.1700
Data Index: 6457646 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9179. Min Act: -0.1700
Data Index: 1131061 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9338. Min Act: -0.1699
Data Index: 3201087 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9179. Min Act: -0.1700
Data Index: 4851798 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9021. Min Act: -0.1699
Data Index: 991738 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9021. Min Act: -0.1700
Data Index: 1267039 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9021. Min Act: -0.1700
Data Index: 950981 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.9021. Min Act: -0.1699
Data Index: 7424212 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.8862. Min Act: -0.1700
Data Index: 5324788 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1390. Min Range: -3.1390
Max Act: 2.8862. Min Act: -0.1690
Data Index: 6296601 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19