Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3820 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.3837. Min Act: -0.1700
Data Index: 478798 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.2900. Min Act: -0.1700
Data Index: 4613563 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.2275. Min Act: -0.1700
Data Index: 8320201 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.1650. Min Act: -0.1700
Data Index: 3004538 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.1025. Min Act: -0.1700
Data Index: 3064120 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.0400. Min Act: -0.1700
Data Index: 5877920 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.0400. Min Act: -0.1700
Data Index: 283254 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.0712. Min Act: -0.1700
Data Index: 4336669 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.0087. Min Act: -0.1700
Data Index: 8335860 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.0087. Min Act: -0.1700
Data Index: 4248282 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.0087. Min Act: -0.1700
Data Index: 28477 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3837. Min Range: -5.3837
Max Act: 5.0087. Min Act: -0.1700
Data Index: 4039402 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3837. Min Range: -5.3837
Max Act: 4.9775. Min Act: -0.1700
Data Index: 719532 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3837. Min Range: -5.3837
Max Act: 4.9775. Min Act: -0.1700
Data Index: 3060736 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3837. Min Range: -5.3837
Max Act: 4.9775. Min Act: -0.1700
Data Index: 1293591 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3837. Min Range: -5.3837
Max Act: 4.9462. Min Act: -0.1700
Data Index: 7477925 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3837. Min Range: -5.3837
Max Act: 4.9775. Min Act: -0.1700
Data Index: 5161295 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3837. Min Range: -5.3837
Max Act: 4.9150. Min Act: -0.1700
Data Index: 2859080 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3837. Min Range: -5.3837
Max Act: 4.9462. Min Act: -0.1700
Data Index: 2094567 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3837. Min Range: -5.3837
Max Act: 4.9462. Min Act: -0.1700
Data Index: 5151871 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19