Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2807 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.7646. Min Act: -0.1700
Data Index: 5794306 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.6396. Min Act: -0.1700
Data Index: 984209 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.6396. Min Act: -0.1700
Data Index: 5210959 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.4833. Min Act: -0.1700
Data Index: 6351306 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.3271. Min Act: -0.1700
Data Index: 7666796 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.3271. Min Act: -0.1700
Data Index: 4427539 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.2646. Min Act: -0.1700
Data Index: 7092731 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.2646. Min Act: -0.1700
Data Index: 4376471 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.2333. Min Act: -0.1700
Data Index: 4755525 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.2333. Min Act: -0.1700
Data Index: 4324598 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.2333. Min Act: -0.1700
Data Index: 2988876 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.1708. Min Act: -0.1700
Data Index: 1982056 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.1708. Min Act: -0.1700
Data Index: 5609596 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.1083. Min Act: -0.1700
Data Index: 7628937 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.0771. Min Act: -0.1700
Data Index: 4733669 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.0771. Min Act: -0.1700
Data Index: 7018901 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.0458. Min Act: -0.1700
Data Index: 5652869 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.0458. Min Act: -0.1700
Data Index: 8786743 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.0458. Min Act: -0.1700
Data Index: 3651950 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7646. Min Range: -7.7646
Max Act: 7.0458. Min Act: -0.1700
Data Index: 8699211 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19