Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1129 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.7175. Min Act: -0.1700
Data Index: 7806798 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.3112. Min Act: -0.1700
Data Index: 4661273 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.2800. Min Act: -0.1700
Data Index: 8622972 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.2800. Min Act: -0.1700
Data Index: 8297526 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.2800. Min Act: -0.1700
Data Index: 7190497 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.2487. Min Act: -0.1700
Data Index: 3535327 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.2487. Min Act: -0.1700
Data Index: 3396652 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.2487. Min Act: -0.1700
Data Index: 7161833 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.2175. Min Act: -0.1700
Data Index: 7000392 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.2175. Min Act: -0.1700
Data Index: 7723614 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.1862. Min Act: -0.1700
Data Index: 5201132 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.1550. Min Act: -0.1700
Data Index: 5358387 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.0925. Min Act: -0.1700
Data Index: 2941053 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.1237. Min Act: -0.1700
Data Index: 4676819 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.0612. Min Act: -0.1700
Data Index: 5642993 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.0925. Min Act: -0.1700
Data Index: 6285160 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.0612. Min Act: -0.1700
Data Index: 5527541 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.0300. Min Act: -0.1700
Data Index: 5487190 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.0612. Min Act: -0.1700
Data Index: 7878422 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7175. Min Range: -7.7175
Max Act: 7.0300. Min Act: -0.1700
Data Index: 6332808 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19