Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5545 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6576. Min Range: -8.6576
Max Act: 8.6576. Min Act: -0.1700
Data Index: 451158 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6576. Min Range: -8.6576
Max Act: 8.0951. Min Act: -0.1700
Data Index: 6616153 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6576. Min Range: -8.6576
Max Act: 8.0951. Min Act: -0.1700
Data Index: 4484073 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6576. Min Range: -8.6576
Max Act: 8.0951. Min Act: -0.1700
Data Index: 3369638 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6576. Min Range: -8.6576
Max Act: 8.0951. Min Act: -0.1700
Data Index: 4561247 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.9076. Min Act: -0.1700
Data Index: 6727446 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.8451. Min Act: -0.1700
Data Index: 17747 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.8451. Min Act: -0.1700
Data Index: 2338035 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.8451. Min Act: -0.1700
Data Index: 8792213 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.7201. Min Act: -0.1700
Data Index: 4919030 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.7201. Min Act: -0.1700
Data Index: 4733220 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.7201. Min Act: -0.1700
Data Index: 4849858 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.7201. Min Act: -0.1700
Data Index: 3586132 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.6576. Min Act: -0.1700
Data Index: 5943792 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.6576. Min Act: -0.1700
Data Index: 5873898 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.6576. Min Act: -0.1700
Data Index: 5000954 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.6576. Min Act: -0.1700
Data Index: 4991443 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.7201. Min Act: -0.1700
Data Index: 1542750 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.5951. Min Act: -0.1700
Data Index: 232941 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6576. Min Range: -8.6576
Max Act: 7.5951. Min Act: -0.1700
Data Index: 2117947 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19