Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2663. Min Range: -5.2663
Max Act: 5.2663. Min Act: -0.1700
Data Index: 1526877 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.8600. Min Act: -0.1700
Data Index: 6300472 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.7975. Min Act: -0.1700
Data Index: 6579056 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.7975. Min Act: -0.1700
Data Index: 6658299 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.7663. Min Act: -0.1700
Data Index: 415793 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.7663. Min Act: -0.1700
Data Index: 4006993 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.7350. Min Act: -0.1700
Data Index: 7499186 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.7350. Min Act: -0.1700
Data Index: 1140815 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.7663. Min Act: -0.1700
Data Index: 5471817 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.7038. Min Act: -0.1700
Data Index: 801808 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.7038. Min Act: -0.1700
Data Index: 8071264 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.7038. Min Act: -0.1700
Data Index: 2752855 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.6413. Min Act: -0.1700
Data Index: 5398489 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.6413. Min Act: -0.1700
Data Index: 4217411 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.6100. Min Act: -0.1700
Data Index: 4938221 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.6100. Min Act: -0.1700
Data Index: 5756460 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.5788. Min Act: -0.1700
Data Index: 3340996 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.5475. Min Act: -0.1700
Data Index: 2179760 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.5475. Min Act: -0.1700
Data Index: 1977298 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2663. Min Range: -5.2663
Max Act: 4.5163. Min Act: -0.1700
Data Index: 5927926 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19