Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.4646. Min Act: -0.1700
Data Index: 8310683 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.4489. Min Act: -0.1700
Data Index: 6616063 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.3862. Min Act: -0.1700
Data Index: 4578741 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.3862. Min Act: -0.1700
Data Index: 8264452 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.3235. Min Act: -0.1700
Data Index: 1046662 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.3235. Min Act: -0.1700
Data Index: 2022872 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.3078. Min Act: -0.1700
Data Index: 8310682 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.2764. Min Act: -0.1700
Data Index: 5311418 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.2764. Min Act: -0.1700
Data Index: 8146350 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.2450. Min Act: -0.1700
Data Index: 6616060 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.2450. Min Act: -0.1700
Data Index: 8310677 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.2450. Min Act: -0.1700
Data Index: 8310680 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.2293. Min Act: -0.1700
Data Index: 8310678 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.2293. Min Act: -0.1700
Data Index: 6896716 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.2450. Min Act: -0.1700
Data Index: 260171 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.2450. Min Act: -0.1700
Data Index: 4935012 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.2135. Min Act: -0.1700
Data Index: 5743175 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.1978. Min Act: -0.1700
Data Index: 8310675 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.1821. Min Act: -0.1700
Data Index: 5559147 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4646. Min Range: -3.4646
Max Act: 3.1821. Min Act: -0.1700
Data Index: 8310679 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19