Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5297 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0932. Min Range: -7.0932
Max Act: 7.0932. Min Act: -0.1700
Data Index: 5951954 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.9682. Min Act: -0.1700
Data Index: 1040890 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.8744. Min Act: -0.1700
Data Index: 1557870 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.8432. Min Act: -0.1700
Data Index: 338816 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.8119. Min Act: -0.1700
Data Index: 510880 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.8119. Min Act: -0.1700
Data Index: 4968551 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.7494. Min Act: -0.1700
Data Index: 1982750 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.7182. Min Act: -0.1700
Data Index: 4837751 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.6557. Min Act: -0.1700
Data Index: 227128 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.6557. Min Act: -0.1700
Data Index: 7253672 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.5932. Min Act: -0.1700
Data Index: 8583313 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.5307. Min Act: -0.1700
Data Index: 1208837 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.5619. Min Act: -0.1700
Data Index: 4577347 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.5307. Min Act: -0.1700
Data Index: 8478661 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.4994. Min Act: -0.1700
Data Index: 6150969 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.4994. Min Act: -0.1700
Data Index: 449004 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.4682. Min Act: -0.1700
Data Index: 8519220 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.4682. Min Act: -0.1700
Data Index: 3537798 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.4682. Min Act: -0.1700
Data Index: 312724 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0932. Min Range: -7.0932
Max Act: 6.4682. Min Act: -0.1700
Data Index: 7216030 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19