Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.6719. Min Act: -0.1700
Data Index: 4333582 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.3970. Min Act: -0.1700
Data Index: 7719284 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.3643. Min Act: -0.1700
Data Index: 5332329 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.3480. Min Act: -0.1700
Data Index: 4765027 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.3316. Min Act: -0.1700
Data Index: 7020167 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.3316. Min Act: -0.1700
Data Index: 1317377 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.3316. Min Act: -0.1700
Data Index: 5261917 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2822. Min Act: -0.1700
Data Index: 1638222 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2822. Min Act: -0.1700
Data Index: 5195327 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2492. Min Act: -0.1700
Data Index: 2463961 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2492. Min Act: -0.1700
Data Index: 3107986 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2492. Min Act: -0.1700
Data Index: 6456119 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2492. Min Act: -0.1700
Data Index: 4531481 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2327. Min Act: -0.1700
Data Index: 4043488 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2161. Min Act: -0.1700
Data Index: 6217599 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2161. Min Act: -0.1700
Data Index: 4220407 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2327. Min Act: -0.1700
Data Index: 5597300 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2327. Min Act: -0.1700
Data Index: 6755101 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2327. Min Act: -0.1700
Data Index: 2969165 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6719. Min Range: -2.6719
Max Act: 2.2327. Min Act: -0.1700
Data Index: 72792 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19