Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 92 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.3437. Min Act: -0.1700
Data Index: 2360812 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.3125. Min Act: -0.1700
Data Index: 7285352 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.2812. Min Act: -0.1700
Data Index: 4064081 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.2812. Min Act: -0.1700
Data Index: 8110591 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.2500. Min Act: -0.1700
Data Index: 5961214 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.2187. Min Act: -0.1700
Data Index: 1486125 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.2187. Min Act: -0.1700
Data Index: 5970202 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1875. Min Act: -0.1700
Data Index: 5676747 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1875. Min Act: -0.1700
Data Index: 4054312 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1875. Min Act: -0.1700
Data Index: 6830932 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1875. Min Act: -0.1700
Data Index: 5486726 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1875. Min Act: -0.1700
Data Index: 7136657 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1562. Min Act: -0.1700
Data Index: 5589373 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1562. Min Act: -0.1700
Data Index: 3732398 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1250. Min Act: -0.1700
Data Index: 7919346 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1562. Min Act: -0.1700
Data Index: 7883959 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1562. Min Act: -0.1700
Data Index: 2884938 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1562. Min Act: -0.1700
Data Index: 8649316 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1562. Min Act: -0.1700
Data Index: 681151 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3437. Min Range: -5.3437
Max Act: 5.1250. Min Act: -0.1700
Data Index: 755859 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19