Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3270 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6248. Min Range: -7.6248
Max Act: 7.6248. Min Act: -0.1700
Data Index: 1760288 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6248. Min Range: -7.6248
Max Act: 7.2498. Min Act: -0.1700
Data Index: 6211723 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6248. Min Range: -7.6248
Max Act: 7.0935. Min Act: -0.1700
Data Index: 2138609 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6248. Min Range: -7.6248
Max Act: 7.0623. Min Act: -0.1700
Data Index: 1202935 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6248. Min Range: -7.6248
Max Act: 7.0310. Min Act: -0.1700
Data Index: 5344135 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.9998. Min Act: -0.1700
Data Index: 6316200 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6248. Min Range: -7.6248
Max Act: 7.0310. Min Act: -0.1700
Data Index: 1760283 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.9685. Min Act: -0.1700
Data Index: 7943643 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.9060. Min Act: -0.1700
Data Index: 4849882 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.9060. Min Act: -0.1700
Data Index: 7688339 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.8748. Min Act: -0.1700
Data Index: 5109736 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.8748. Min Act: -0.1700
Data Index: 6267842 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.8748. Min Act: -0.1700
Data Index: 8501421 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.8435. Min Act: -0.1700
Data Index: 7160158 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.8435. Min Act: -0.1700
Data Index: 4873639 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.8123. Min Act: -0.1700
Data Index: 4754173 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.8123. Min Act: -0.1700
Data Index: 6726895 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.8435. Min Act: -0.1700
Data Index: 3449740 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.7810. Min Act: -0.1700
Data Index: 6132153 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6248. Min Range: -7.6248
Max Act: 6.7498. Min Act: -0.1700
Data Index: 3698701 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #19