Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.5015. Min Act: -0.1700
Data Index: 8770350 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.3134. Min Act: -0.1700
Data Index: 3852147 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.2663. Min Act: -0.1700
Data Index: 8701103 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.2348. Min Act: -0.1700
Data Index: 6229804 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.2505. Min Act: -0.1700
Data Index: 6232108 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.1877. Min Act: -0.1700
Data Index: 1212292 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.1562. Min Act: -0.1700
Data Index: 6232106 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.1405. Min Act: -0.1700
Data Index: 5545956 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.1562. Min Act: -0.1700
Data Index: 293238 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.1247. Min Act: -0.1700
Data Index: 5305552 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.1247. Min Act: -0.1700
Data Index: 1797271 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.0932. Min Act: -0.1700
Data Index: 2807252 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.1089. Min Act: -0.1700
Data Index: 3270663 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.0932. Min Act: -0.1700
Data Index: 1106859 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.0774. Min Act: -0.1700
Data Index: 5321630 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.0774. Min Act: -0.1700
Data Index: 4844395 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.0774. Min Act: -0.1700
Data Index: 2173212 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.0459. Min Act: -0.1700
Data Index: 7690552 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.0301. Min Act: -0.1700
Data Index: 3156806 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5015. Min Range: -3.5015
Max Act: 3.0459. Min Act: -0.1700
Data Index: 8107675 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19