Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.6366. Min Act: -0.1700
Data Index: 7259265 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.5741. Min Act: -0.1700
Data Index: 5994667 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.5116. Min Act: -0.1700
Data Index: 4192633 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.4491. Min Act: -0.1700
Data Index: 6065120 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.4179. Min Act: -0.1700
Data Index: 1386436 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.3554. Min Act: -0.1700
Data Index: 5644708 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.2929. Min Act: -0.1700
Data Index: 3649928 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.2304. Min Act: -0.1700
Data Index: 195755 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.2616. Min Act: -0.1700
Data Index: 3812632 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.2304. Min Act: -0.1700
Data Index: 2113744 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.2304. Min Act: -0.1700
Data Index: 1493470 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.1991. Min Act: -0.1700
Data Index: 3213030 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.1991. Min Act: -0.1700
Data Index: 5940955 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.1679. Min Act: -0.1700
Data Index: 7010705 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.1991. Min Act: -0.1700
Data Index: 7829684 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.1679. Min Act: -0.1700
Data Index: 3072638 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.1366. Min Act: -0.1700
Data Index: 2363962 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.1366. Min Act: -0.1700
Data Index: 989783 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.1366. Min Act: -0.1700
Data Index: 3141954 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6366. Min Range: -6.6366
Max Act: 6.1054. Min Act: -0.1700
Data Index: 3716627 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19