Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2653 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2900. Min Range: -8.2900
Max Act: 8.2900. Min Act: -0.1700
Data Index: 7466782 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2900. Min Range: -8.2900
Max Act: 8.1650. Min Act: -0.1700
Data Index: 4102643 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2900. Min Range: -8.2900
Max Act: 8.1650. Min Act: -0.1700
Data Index: 4128587 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2900. Min Range: -8.2900
Max Act: 8.0087. Min Act: -0.1700
Data Index: 766676 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2900. Min Range: -8.2900
Max Act: 8.0400. Min Act: -0.1700
Data Index: 1875236 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2900. Min Range: -8.2900
Max Act: 8.0400. Min Act: -0.1700
Data Index: 351956 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.9462. Min Act: -0.1700
Data Index: 1299464 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.8212. Min Act: -0.1700
Data Index: 7444444 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.8212. Min Act: -0.1700
Data Index: 3350310 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.8212. Min Act: -0.1700
Data Index: 646670 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.7900. Min Act: -0.1700
Data Index: 7276185 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.8212. Min Act: -0.1700
Data Index: 7763605 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.7900. Min Act: -0.1700
Data Index: 7444442 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.7587. Min Act: -0.1700
Data Index: 320167 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.7587. Min Act: -0.1700
Data Index: 312635 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.7587. Min Act: -0.1700
Data Index: 7963792 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.6962. Min Act: -0.1700
Data Index: 6694767 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.7587. Min Act: -0.1700
Data Index: 1707197 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.7275. Min Act: -0.1700
Data Index: 1434935 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2900. Min Range: -8.2900
Max Act: 7.7275. Min Act: -0.1700
Data Index: 6622513 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19