Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2761 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.4018. Min Act: -0.1700
Data Index: 6532688 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.3705. Min Act: -0.1700
Data Index: 7086265 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.2455. Min Act: -0.1700
Data Index: 3389553 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.2455. Min Act: -0.1700
Data Index: 6904411 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.2143. Min Act: -0.1700
Data Index: 7677542 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.2455. Min Act: -0.1700
Data Index: 7086263 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.1830. Min Act: -0.1700
Data Index: 2626576 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.1830. Min Act: -0.1700
Data Index: 6999594 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.1518. Min Act: -0.1700
Data Index: 6578878 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.2143. Min Act: -0.1700
Data Index: 7086259 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.1518. Min Act: -0.1700
Data Index: 7086267 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.1518. Min Act: -0.1700
Data Index: 8519203 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.1518. Min Act: -0.1700
Data Index: 7086258 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.1518. Min Act: -0.1700
Data Index: 3781379 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.1518. Min Act: -0.1700
Data Index: 8544355 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.1205. Min Act: -0.1700
Data Index: 3643305 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.1518. Min Act: -0.1700
Data Index: 4306313 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.0893. Min Act: -0.1700
Data Index: 7086256 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.0893. Min Act: -0.1700
Data Index: 4050084 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4018. Min Range: -5.4018
Max Act: 5.0893. Min Act: -0.1700
Data Index: 4832665 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19