Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2401 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.7544. Min Act: -0.1700
Data Index: 2511946 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.7232. Min Act: -0.1700
Data Index: 6342107 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.7232. Min Act: -0.1700
Data Index: 609212 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.7232. Min Act: -0.1700
Data Index: 3624777 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6919. Min Act: -0.1700
Data Index: 1801295 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6919. Min Act: -0.1700
Data Index: 3491873 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6607. Min Act: -0.1700
Data Index: 6037776 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6607. Min Act: -0.1700
Data Index: 8504327 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6607. Min Act: -0.1700
Data Index: 8129525 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6607. Min Act: -0.1700
Data Index: 7986909 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6294. Min Act: -0.1700
Data Index: 5290005 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6294. Min Act: -0.1700
Data Index: 8070412 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6294. Min Act: -0.1700
Data Index: 6502551 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6294. Min Act: -0.1700
Data Index: 8646294 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5982. Min Act: -0.1699
Data Index: 678217 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6294. Min Act: -0.1700
Data Index: 4246420 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.6294. Min Act: -0.1700
Data Index: 2930036 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5982. Min Act: -0.1700
Data Index: 1589853 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5669. Min Act: -0.1700
Data Index: 3665807 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7544. Min Range: -6.7544
Max Act: 6.5982. Min Act: -0.1700
Data Index: 8428058 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19