Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3684 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3262. Min Range: -7.3262
Max Act: 7.3262. Min Act: -0.1700
Data Index: 2769209 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3262. Min Range: -7.3262
Max Act: 7.0137. Min Act: -0.1700
Data Index: 1066696 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.9824. Min Act: -0.1700
Data Index: 6532731 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.9199. Min Act: -0.1700
Data Index: 5074590 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.8887. Min Act: -0.1700
Data Index: 3512559 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.8887. Min Act: -0.1700
Data Index: 162564 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.8887. Min Act: -0.1700
Data Index: 7339685 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.8574. Min Act: -0.1700
Data Index: 1137 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.8262. Min Act: -0.1700
Data Index: 6459488 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.8262. Min Act: -0.1700
Data Index: 3379764 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.8262. Min Act: -0.1700
Data Index: 1167535 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.7637. Min Act: -0.1700
Data Index: 8070249 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.7637. Min Act: -0.1700
Data Index: 7888524 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.7637. Min Act: -0.1700
Data Index: 1828511 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.7949. Min Act: -0.1700
Data Index: 3223024 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.7324. Min Act: -0.1700
Data Index: 8472957 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.7637. Min Act: -0.1700
Data Index: 3269493 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.6699. Min Act: -0.1700
Data Index: 2534800 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.6699. Min Act: -0.1700
Data Index: 7360993 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3262. Min Range: -7.3262
Max Act: 6.6387. Min Act: -0.1700
Data Index: 1182345 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19