Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.9119. Min Act: -0.1700
Data Index: 2427613 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.9119. Min Act: -0.1700
Data Index: 667331 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.8494. Min Act: -0.1700
Data Index: 6370731 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.8181. Min Act: -0.1700
Data Index: 1110990 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.7244. Min Act: -0.1700
Data Index: 2270634 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.7244. Min Act: -0.1700
Data Index: 3831946 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.7244. Min Act: -0.1700
Data Index: 8458919 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.7244. Min Act: -0.1700
Data Index: 7280698 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6931. Min Act: -0.1700
Data Index: 4008378 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6619. Min Act: -0.1700
Data Index: 4624989 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6619. Min Act: -0.1700
Data Index: 6831337 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6619. Min Act: -0.1700
Data Index: 4032034 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6619. Min Act: -0.1700
Data Index: 6021143 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6306. Min Act: -0.1700
Data Index: 5592687 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6306. Min Act: -0.1700
Data Index: 6652150 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6306. Min Act: -0.1700
Data Index: 1554811 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6306. Min Act: -0.1700
Data Index: 8751363 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6306. Min Act: -0.1700
Data Index: 2604520 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.6306. Min Act: -0.1700
Data Index: 6199816 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9119. Min Range: -4.9119
Max Act: 4.5994. Min Act: -0.1700
Data Index: 3364572 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19