Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2030. Min Range: -6.2030
Max Act: 6.1405. Min Act: -0.1700
Data Index: 6701256 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2030. Min Range: -6.2030
Max Act: 6.2030. Min Act: -0.1700
Data Index: 7274691 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2030. Min Range: -6.2030
Max Act: 6.0467. Min Act: -0.1700
Data Index: 477321 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2030. Min Range: -6.2030
Max Act: 6.0155. Min Act: -0.1700
Data Index: 4579313 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.8592. Min Act: -0.1700
Data Index: 1366740 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.8592. Min Act: -0.1700
Data Index: 6403043 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.7967. Min Act: -0.1700
Data Index: 2591691 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.7655. Min Act: -0.1700
Data Index: 7572447 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.7342. Min Act: -0.1700
Data Index: 8241357 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.7342. Min Act: -0.1700
Data Index: 3478553 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.7030. Min Act: -0.1700
Data Index: 4296376 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.7030. Min Act: -0.1700
Data Index: 6506924 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.7030. Min Act: -0.1700
Data Index: 8442478 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.6717. Min Act: -0.1700
Data Index: 5122279 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.6717. Min Act: -0.1700
Data Index: 3246091 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.6405. Min Act: -0.1700
Data Index: 2790296 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.6405. Min Act: -0.1700
Data Index: 3536772 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.6405. Min Act: -0.1700
Data Index: 6019363 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.6092. Min Act: -0.1700
Data Index: 7672270 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2030. Min Range: -6.2030
Max Act: 5.6092. Min Act: -0.1700
Data Index: 1792993 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19