Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3235 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.3622. Min Act: -0.1700
Data Index: 6838286 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.3310. Min Act: -0.1700
Data Index: 8268677 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.3310. Min Act: -0.1700
Data Index: 7732278 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.2997. Min Act: -0.1700
Data Index: 6363321 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.2997. Min Act: -0.1700
Data Index: 2948512 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.2997. Min Act: -0.1700
Data Index: 6623020 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.2372. Min Act: -0.1700
Data Index: 8339429 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.2060. Min Act: -0.1700
Data Index: 8599757 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1747. Min Act: -0.1700
Data Index: 4169116 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1747. Min Act: -0.1700
Data Index: 3691471 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 3069545 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 6580176 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 6519984 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 7784474 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 2074909 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 6883471 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 4938990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 3491698 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.0810. Min Act: -0.1700
Data Index: 6882659 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.0810. Min Act: -0.1700
Data Index: 7231065 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19