Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.4105. Min Act: -0.1700
Data Index: 8206681 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.1918. Min Act: -0.1700
Data Index: 7587306 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.1293. Min Act: -0.1700
Data Index: 7713248 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.1293. Min Act: -0.1700
Data Index: 5027650 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.0668. Min Act: -0.1700
Data Index: 1577149 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.0043. Min Act: -0.1700
Data Index: 5727500 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.0043. Min Act: -0.1700
Data Index: 4533672 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4105. Min Range: -7.4105
Max Act: 7.0043. Min Act: -0.1700
Data Index: 1257370 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.9730. Min Act: -0.1700
Data Index: 5410969 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.9418. Min Act: -0.1700
Data Index: 7869257 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.9418. Min Act: -0.1700
Data Index: 1013803 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.9418. Min Act: -0.1700
Data Index: 7823587 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.9105. Min Act: -0.1700
Data Index: 3543155 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.9105. Min Act: -0.1700
Data Index: 7735298 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8793. Min Act: -0.1700
Data Index: 6400185 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8793. Min Act: -0.1700
Data Index: 5536847 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8480. Min Act: -0.1700
Data Index: 6391267 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8480. Min Act: -0.1700
Data Index: 6866990 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8480. Min Act: -0.1700
Data Index: 7469993 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4105. Min Range: -7.4105
Max Act: 6.8480. Min Act: -0.1700
Data Index: 7563455 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19