Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1678 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0676. Min Range: -7.0676
Max Act: 7.0676. Min Act: -0.1700
Data Index: 5557336 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.8801. Min Act: -0.1700
Data Index: 3498779 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.8489. Min Act: -0.1700
Data Index: 8233926 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.6301. Min Act: -0.1700
Data Index: 3133710 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.5051. Min Act: -0.1700
Data Index: 7326325 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.4739. Min Act: -0.1700
Data Index: 6660314 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.4426. Min Act: -0.1700
Data Index: 5247988 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.4114. Min Act: -0.1700
Data Index: 4499315 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.4114. Min Act: -0.1700
Data Index: 1536749 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.4114. Min Act: -0.1700
Data Index: 5629115 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.3801. Min Act: -0.1700
Data Index: 6850551 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.3176. Min Act: -0.1700
Data Index: 8070642 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.3176. Min Act: -0.1700
Data Index: 4865275 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.3176. Min Act: -0.1700
Data Index: 861187 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.3176. Min Act: -0.1700
Data Index: 1716343 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.2551. Min Act: -0.1700
Data Index: 7312630 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.2551. Min Act: -0.1700
Data Index: 4397727 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.2551. Min Act: -0.1700
Data Index: 605436 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.2551. Min Act: -0.1700
Data Index: 2290673 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0676. Min Range: -7.0676
Max Act: 6.2551. Min Act: -0.1700
Data Index: 3847665 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19