Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1473 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1092. Min Range: -6.1092
Max Act: 6.1092. Min Act: -0.1700
Data Index: 8493570 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1092. Min Range: -6.1092
Max Act: 6.0780. Min Act: -0.1700
Data Index: 1292928 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.9530. Min Act: -0.1700
Data Index: 3809259 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.9217. Min Act: -0.1700
Data Index: 3691332 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.8592. Min Act: -0.1700
Data Index: 1064116 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.8592. Min Act: -0.1700
Data Index: 4053082 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.8280. Min Act: -0.1700
Data Index: 1084392 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.8280. Min Act: -0.1700
Data Index: 8257873 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.8592. Min Act: -0.1700
Data Index: 7743530 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7967. Min Act: -0.1700
Data Index: 1084395 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7967. Min Act: -0.1700
Data Index: 958558 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7967. Min Act: -0.1700
Data Index: 4235343 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7655. Min Act: -0.1700
Data Index: 4103217 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7655. Min Act: -0.1700
Data Index: 3594416 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7342. Min Act: -0.1700
Data Index: 849076 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7342. Min Act: -0.1700
Data Index: 7673302 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7342. Min Act: -0.1700
Data Index: 7941868 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7342. Min Act: -0.1700
Data Index: 1084396 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7030. Min Act: -0.1700
Data Index: 3089096 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1092. Min Range: -6.1092
Max Act: 5.7030. Min Act: -0.1700
Data Index: 7203836 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19