Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4846 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.5036. Min Act: -0.1700
Data Index: 3846487 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4723. Min Act: -0.1700
Data Index: 4244686 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4411. Min Act: -0.1700
Data Index: 4997816 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4411. Min Act: -0.1700
Data Index: 3532400 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4098. Min Act: -0.1700
Data Index: 5981146 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4098. Min Act: -0.1700
Data Index: 4493301 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4098. Min Act: -0.1700
Data Index: 4394309 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4098. Min Act: -0.1700
Data Index: 2027143 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4098. Min Act: -0.1700
Data Index: 2927724 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4098. Min Act: -0.1700
Data Index: 3639447 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4098. Min Act: -0.1700
Data Index: 7462023 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4098. Min Act: -0.1700
Data Index: 6968067 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3786. Min Act: -0.1700
Data Index: 1575634 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4098. Min Act: -0.1700
Data Index: 5287003 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3786. Min Act: -0.1700
Data Index: 4038284 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.4098. Min Act: -0.1700
Data Index: 2896765 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3786. Min Act: -0.1700
Data Index: 67716 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3786. Min Act: -0.1700
Data Index: 3775359 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3786. Min Act: -0.1700
Data Index: 1253593 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5036. Min Range: -4.5036
Max Act: 4.3786. Min Act: -0.1700
Data Index: 355324 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19