Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 587 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4338. Min Range: -7.4338
Max Act: 7.4338. Min Act: -0.1700
Data Index: 8704770 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4338. Min Range: -7.4338
Max Act: 7.3088. Min Act: -0.1700
Data Index: 3615374 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4338. Min Range: -7.4338
Max Act: 7.1213. Min Act: -0.1700
Data Index: 6472957 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4338. Min Range: -7.4338
Max Act: 7.1213. Min Act: -0.1700
Data Index: 5884624 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4338. Min Range: -7.4338
Max Act: 7.0901. Min Act: -0.1700
Data Index: 1024107 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.9963. Min Act: -0.1700
Data Index: 1932341 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.9963. Min Act: -0.1700
Data Index: 7473402 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.9963. Min Act: -0.1700
Data Index: 5060783 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.9338. Min Act: -0.1700
Data Index: 3126809 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.9338. Min Act: -0.1700
Data Index: 5099983 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.9026. Min Act: -0.1700
Data Index: 1490912 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.8713. Min Act: -0.1700
Data Index: 402663 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.8713. Min Act: -0.1700
Data Index: 6212342 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.8713. Min Act: -0.1700
Data Index: 8142209 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.8401. Min Act: -0.1700
Data Index: 5321605 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.8088. Min Act: -0.1700
Data Index: 7613286 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.7776. Min Act: -0.1700
Data Index: 5791656 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.8088. Min Act: -0.1700
Data Index: 4238254 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.8401. Min Act: -0.1700
Data Index: 4524311 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4338. Min Range: -7.4338
Max Act: 6.8088. Min Act: -0.1700
Data Index: 957758 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19