Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1324 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.3690. Min Act: -0.1700
Data Index: 2129728 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.3533. Min Act: -0.1700
Data Index: 5181844 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.2591. Min Act: -0.1700
Data Index: 2849923 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.2591. Min Act: -0.1700
Data Index: 4561470 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.2120. Min Act: -0.1700
Data Index: 4203726 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1963. Min Act: -0.1700
Data Index: 4993618 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.2120. Min Act: -0.1700
Data Index: 3140652 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1648. Min Act: -0.1700
Data Index: 2416607 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1648. Min Act: -0.1700
Data Index: 6181689 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1648. Min Act: -0.1700
Data Index: 7681546 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1333. Min Act: -0.1700
Data Index: 1587359 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1491. Min Act: -0.1700
Data Index: 46291 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1491. Min Act: -0.1700
Data Index: 1732468 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1333. Min Act: -0.1700
Data Index: 4982138 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1176. Min Act: -0.1700
Data Index: 1600090 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1176. Min Act: -0.1700
Data Index: 4530042 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1018. Min Act: -0.1700
Data Index: 6949603 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1176. Min Act: -0.1700
Data Index: 1260034 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.0860. Min Act: -0.1700
Data Index: 3871322 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3690. Min Range: -3.3690
Max Act: 3.1176. Min Act: -0.1700
Data Index: 6609518 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19