Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.3886. Min Act: -0.1700
Data Index: 7127868 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.3886. Min Act: -0.1700
Data Index: 2594484 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.3261. Min Act: -0.1700
Data Index: 5489776 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2948. Min Act: -0.1700
Data Index: 2324728 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2948. Min Act: -0.1700
Data Index: 8752998 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2948. Min Act: -0.1700
Data Index: 2653766 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2636. Min Act: -0.1700
Data Index: 8218181 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2323. Min Act: -0.1700
Data Index: 745283 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2011. Min Act: -0.1700
Data Index: 4250296 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2323. Min Act: -0.1700
Data Index: 4727987 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1698. Min Act: -0.1700
Data Index: 370354 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2011. Min Act: -0.1700
Data Index: 8094342 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.2011. Min Act: -0.1700
Data Index: 6879007 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1698. Min Act: -0.1699
Data Index: 8473709 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1698. Min Act: -0.1700
Data Index: 6220446 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1698. Min Act: -0.1700
Data Index: 1237964 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1698. Min Act: -0.1700
Data Index: 5676238 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1698. Min Act: -0.1700
Data Index: 891459 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1698. Min Act: -0.1700
Data Index: 1585577 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3886. Min Range: -5.3886
Max Act: 5.1698. Min Act: -0.1700
Data Index: 2711377 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19