Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.3928. Min Act: -0.1700
Data Index: 6542878 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.3615. Min Act: -0.1700
Data Index: 5613903 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.3303. Min Act: -0.1700
Data Index: 2323429 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.2990. Min Act: -0.1700
Data Index: 7403675 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.2678. Min Act: -0.1700
Data Index: 4167782 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.1428. Min Act: -0.1700
Data Index: 3199409 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.1115. Min Act: -0.1700
Data Index: 8187902 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.0803. Min Act: -0.1700
Data Index: 8646229 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.0803. Min Act: -0.1700
Data Index: 2124206 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.0803. Min Act: -0.1700
Data Index: 2982752 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.0803. Min Act: -0.1700
Data Index: 5544826 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.0803. Min Act: -0.1700
Data Index: 1620695 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.0178. Min Act: -0.1700
Data Index: 413900 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.0178. Min Act: -0.1700
Data Index: 8460084 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.0178. Min Act: -0.1700
Data Index: 3720884 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3928. Min Range: -6.3928
Max Act: 6.0178. Min Act: -0.1700
Data Index: 7063739 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3928. Min Range: -6.3928
Max Act: 5.9865. Min Act: -0.1700
Data Index: 3193103 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3928. Min Range: -6.3928
Max Act: 5.9553. Min Act: -0.1700
Data Index: 1178966 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3928. Min Range: -6.3928
Max Act: 5.9865. Min Act: -0.1700
Data Index: 5024866 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3928. Min Range: -6.3928
Max Act: 5.9240. Min Act: -0.1700
Data Index: 7002436 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19