Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5429 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.9581. Min Act: -0.1700
Data Index: 4844578 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.8643. Min Act: -0.1700
Data Index: 7716566 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.8018. Min Act: -0.1700
Data Index: 5758174 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.7706. Min Act: -0.1700
Data Index: 970532 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.7706. Min Act: -0.1700
Data Index: 5126345 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.7393. Min Act: -0.1700
Data Index: 7693220 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.7393. Min Act: -0.1700
Data Index: 2081858 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.7393. Min Act: -0.1700
Data Index: 5635163 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.7081. Min Act: -0.1700
Data Index: 6114257 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.7081. Min Act: -0.1700
Data Index: 3408084 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.7081. Min Act: -0.1700
Data Index: 3021449 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.6768. Min Act: -0.1700
Data Index: 1371565 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.6768. Min Act: -0.1700
Data Index: 5644345 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.6456. Min Act: -0.1700
Data Index: 3287300 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.6456. Min Act: -0.1700
Data Index: 1646269 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.6456. Min Act: -0.1700
Data Index: 2572023 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.6768. Min Act: -0.1700
Data Index: 2494665 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.6456. Min Act: -0.1700
Data Index: 5580971 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.6143. Min Act: -0.1700
Data Index: 3416126 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9581. Min Range: -5.9581
Max Act: 5.6143. Min Act: -0.1700
Data Index: 1551231 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19