Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1923 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1297. Min Range: -5.1297
Max Act: 5.1297. Min Act: -0.1700
Data Index: 1580335 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1297. Min Range: -5.1297
Max Act: 5.0360. Min Act: -0.1700
Data Index: 1501745 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.9422. Min Act: -0.1700
Data Index: 5423050 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.9422. Min Act: -0.1700
Data Index: 1217260 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.9422. Min Act: -0.1700
Data Index: 6800397 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.9110. Min Act: -0.1700
Data Index: 5699184 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.8172. Min Act: -0.1700
Data Index: 4994777 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.8172. Min Act: -0.1700
Data Index: 8524442 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.7547. Min Act: -0.1700
Data Index: 5070236 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.7235. Min Act: -0.1700
Data Index: 5728098 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.7235. Min Act: -0.1700
Data Index: 8024826 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.6922. Min Act: -0.1700
Data Index: 2526749 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.6610. Min Act: -0.1700
Data Index: 1958686 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.6922. Min Act: -0.1700
Data Index: 6728924 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.6922. Min Act: -0.1700
Data Index: 1719290 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.6297. Min Act: -0.1700
Data Index: 7578541 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.6610. Min Act: -0.1700
Data Index: 5473564 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.6297. Min Act: -0.1700
Data Index: 3212539 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.6297. Min Act: -0.1700
Data Index: 932457 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1297. Min Range: -5.1297
Max Act: 4.6297. Min Act: -0.1700
Data Index: 3678253 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19