Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 435 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1947. Min Range: -13.1947
Max Act: 13.1947. Min Act: -0.1700
Data Index: 1175935 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1947. Min Range: -13.1947
Max Act: 13.1322. Min Act: -0.1700
Data Index: 5711609 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1947. Min Range: -13.1947
Max Act: 13.0697. Min Act: -0.1700
Data Index: 1078730 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1947. Min Range: -13.1947
Max Act: 13.0697. Min Act: -0.1700
Data Index: 5385217 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.9447. Min Act: -0.1700
Data Index: 6121842 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.8822. Min Act: -0.1700
Data Index: 7319568 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.8822. Min Act: -0.1700
Data Index: 3565558 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.7572. Min Act: -0.1700
Data Index: 8310714 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.6947. Min Act: -0.1700
Data Index: 7610855 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.6322. Min Act: -0.1700
Data Index: 685125 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.6947. Min Act: -0.1700
Data Index: 7837090 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.6947. Min Act: -0.1700
Data Index: 796483 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.5697. Min Act: -0.1700
Data Index: 8163304 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.5697. Min Act: -0.1700
Data Index: 299082 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.5697. Min Act: -0.1700
Data Index: 8660977 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.5697. Min Act: -0.1700
Data Index: 1146629 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.5697. Min Act: -0.1700
Data Index: 2317182 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.6322. Min Act: -0.1700
Data Index: 3753729 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.5697. Min Act: -0.1700
Data Index: 6403047 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1947. Min Range: -13.1947
Max Act: 12.5697. Min Act: -0.1700
Data Index: 7739704 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19