Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.8464. Min Act: -0.1700
Data Index: 2161666 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.7839. Min Act: -0.1700
Data Index: 3985837 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.6902. Min Act: -0.1700
Data Index: 6552661 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.6902. Min Act: -0.1700
Data Index: 598630 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.6902. Min Act: -0.1700
Data Index: 4482346 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.6902. Min Act: -0.1700
Data Index: 3430852 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.6589. Min Act: -0.1700
Data Index: 750555 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.6902. Min Act: -0.1700
Data Index: 3294015 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.5964. Min Act: -0.1700
Data Index: 8618004 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.5964. Min Act: -0.1700
Data Index: 2161667 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.6277. Min Act: -0.1700
Data Index: 5703209 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.6277. Min Act: -0.1700
Data Index: 1228350 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.5964. Min Act: -0.1700
Data Index: 8793152 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.5964. Min Act: -0.1700
Data Index: 4171338 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.5652. Min Act: -0.1700
Data Index: 5481333 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.5652. Min Act: -0.1700
Data Index: 6026515 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.5652. Min Act: -0.1700
Data Index: 598632 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.5339. Min Act: -0.1700
Data Index: 2875812 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.5339. Min Act: -0.1700
Data Index: 6677295 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8464. Min Range: -5.8464
Max Act: 5.5027. Min Act: -0.1700
Data Index: 2425331 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19