Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0860. Min Range: -7.0860
Max Act: 7.0860. Min Act: -0.1700
Data Index: 1765737 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.7735. Min Act: -0.1700
Data Index: 7270999 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.6797. Min Act: -0.1700
Data Index: 7375424 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.6485. Min Act: -0.1700
Data Index: 4278319 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.6797. Min Act: -0.1700
Data Index: 1237904 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.4610. Min Act: -0.1700
Data Index: 7693689 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.4297. Min Act: -0.1700
Data Index: 5930934 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.4297. Min Act: -0.1700
Data Index: 4911864 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.3985. Min Act: -0.1700
Data Index: 2794456 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.3985. Min Act: -0.1700
Data Index: 1821211 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.3360. Min Act: -0.1700
Data Index: 569584 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.3360. Min Act: -0.1700
Data Index: 3674819 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.3360. Min Act: -0.1700
Data Index: 6382961 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.3047. Min Act: -0.1700
Data Index: 8035027 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.3047. Min Act: -0.1700
Data Index: 912274 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.2735. Min Act: -0.1700
Data Index: 8009296 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.2735. Min Act: -0.1700
Data Index: 4944482 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.2735. Min Act: -0.1700
Data Index: 2896465 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.2110. Min Act: -0.1700
Data Index: 5289627 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0860. Min Range: -7.0860
Max Act: 6.1797. Min Act: -0.1700
Data Index: 4668770 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19