Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6096 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.7195. Min Act: -0.1700
Data Index: 7946068 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.4695. Min Act: -0.1700
Data Index: 2938618 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.4695. Min Act: -0.1700
Data Index: 8753002 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.4070. Min Act: -0.1700
Data Index: 4596744 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.4070. Min Act: -0.1700
Data Index: 5850717 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.4070. Min Act: -0.1700
Data Index: 3285911 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.3757. Min Act: -0.1700
Data Index: 2951485 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.3445. Min Act: -0.1700
Data Index: 7464000 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.3757. Min Act: -0.1700
Data Index: 1717666 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.2820. Min Act: -0.1700
Data Index: 8424720 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.3132. Min Act: -0.1700
Data Index: 8019846 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.2507. Min Act: -0.1700
Data Index: 631448 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.2507. Min Act: -0.1700
Data Index: 7274582 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.2820. Min Act: -0.1700
Data Index: 381336 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.2507. Min Act: -0.1700
Data Index: 1797661 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.2507. Min Act: -0.1700
Data Index: 884416 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.2507. Min Act: -0.1700
Data Index: 5437885 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.2507. Min Act: -0.1700
Data Index: 2431950 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.2195. Min Act: -0.1700
Data Index: 7072324 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7195. Min Range: -5.7195
Max Act: 5.2195. Min Act: -0.1700
Data Index: 1901602 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19