Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2072 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.4832. Min Act: -0.1700
Data Index: 8191356 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.3582. Min Act: -0.1700
Data Index: 3399135 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.3270. Min Act: -0.1700
Data Index: 869662 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.2957. Min Act: -0.1700
Data Index: 821974 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.2020. Min Act: -0.1700
Data Index: 8546323 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.2020. Min Act: -0.1700
Data Index: 4467836 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1707. Min Act: -0.1700
Data Index: 681409 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1707. Min Act: -0.1700
Data Index: 231319 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1707. Min Act: -0.1700
Data Index: 4940153 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1395. Min Act: -0.1700
Data Index: 7433559 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1395. Min Act: -0.1700
Data Index: 519193 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1395. Min Act: -0.1700
Data Index: 4304186 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1395. Min Act: -0.1700
Data Index: 8701295 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1395. Min Act: -0.1700
Data Index: 7655340 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1395. Min Act: -0.1700
Data Index: 869663 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1082. Min Act: -0.1700
Data Index: 92350 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1082. Min Act: -0.1700
Data Index: 8434675 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1082. Min Act: -0.1700
Data Index: 231323 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1082. Min Act: -0.1700
Data Index: 3171827 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4832. Min Range: -5.4832
Max Act: 5.1082. Min Act: -0.1700
Data Index: 104230 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19