Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2963. Min Range: -7.2963
Max Act: 7.2963. Min Act: -0.1700
Data Index: 3818353 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.9526. Min Act: -0.1700
Data Index: 6515943 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.9213. Min Act: -0.1700
Data Index: 7298765 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.9213. Min Act: -0.1700
Data Index: 6442748 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.9213. Min Act: -0.1700
Data Index: 8059888 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.8901. Min Act: -0.1700
Data Index: 5245977 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.8588. Min Act: -0.1700
Data Index: 4886798 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.8588. Min Act: -0.1700
Data Index: 2763329 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.8276. Min Act: -0.1700
Data Index: 2017926 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.7963. Min Act: -0.1700
Data Index: 4977987 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.7963. Min Act: -0.1700
Data Index: 8625744 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.7651. Min Act: -0.1700
Data Index: 3274215 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.7651. Min Act: -0.1700
Data Index: 4376938 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.7651. Min Act: -0.1700
Data Index: 1422653 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.7338. Min Act: -0.1700
Data Index: 3920090 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.7026. Min Act: -0.1700
Data Index: 6392492 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.7338. Min Act: -0.1700
Data Index: 8701616 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.7026. Min Act: -0.1700
Data Index: 6315590 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.6713. Min Act: -0.1700
Data Index: 8343523 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2963. Min Range: -7.2963
Max Act: 6.6713. Min Act: -0.1700
Data Index: 2701448 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19