Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3018 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.2167. Min Act: -0.1700
Data Index: 4191474 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.1853. Min Act: -0.1700
Data Index: 8611430 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.1381. Min Act: -0.1700
Data Index: 4660841 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.1381. Min Act: -0.1700
Data Index: 1892242 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.1066. Min Act: -0.1700
Data Index: 330477 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0750. Min Act: -0.1700
Data Index: 5237881 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0593. Min Act: -0.1700
Data Index: 6628635 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0435. Min Act: -0.1700
Data Index: 6047290 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0435. Min Act: -0.1700
Data Index: 6216430 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0277. Min Act: -0.1700
Data Index: 2572320 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0277. Min Act: -0.1700
Data Index: 7092609 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0277. Min Act: -0.1700
Data Index: 2578405 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0277. Min Act: -0.1700
Data Index: 8493248 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0119. Min Act: -0.1700
Data Index: 1595534 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0119. Min Act: -0.1700
Data Index: 6014905 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0277. Min Act: -0.1700
Data Index: 7311398 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2167. Min Range: -3.2167
Max Act: 3.0119. Min Act: -0.1700
Data Index: 3030320 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2167. Min Range: -3.2167
Max Act: 2.9961. Min Act: -0.1700
Data Index: 555366 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2167. Min Range: -3.2167
Max Act: 2.9961. Min Act: -0.1700
Data Index: 8253303 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2167. Min Range: -3.2167
Max Act: 2.9803. Min Act: -0.1700
Data Index: 3316593 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19