Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3618 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.9947. Min Act: -0.1700
Data Index: 3091802 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.8384. Min Act: -0.1700
Data Index: 3526022 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.8384. Min Act: -0.1700
Data Index: 7943440 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.6822. Min Act: -0.1700
Data Index: 8742033 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.6822. Min Act: -0.1700
Data Index: 384259 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.6509. Min Act: -0.1700
Data Index: 383655 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.5884. Min Act: -0.1700
Data Index: 2896457 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.5572. Min Act: -0.1700
Data Index: 3319508 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.5259. Min Act: -0.1700
Data Index: 1921819 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4947. Min Act: -0.1700
Data Index: 3923806 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4947. Min Act: -0.1700
Data Index: 3728627 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4009. Min Act: -0.1700
Data Index: 8373273 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4322. Min Act: -0.1700
Data Index: 695974 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4322. Min Act: -0.1700
Data Index: 3854343 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4322. Min Act: -0.1700
Data Index: 810801 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4009. Min Act: -0.1700
Data Index: 5750183 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4009. Min Act: -0.1700
Data Index: 3746625 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4322. Min Act: -0.1700
Data Index: 6800869 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4009. Min Act: -0.1700
Data Index: 751624 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.3697. Min Act: -0.1700
Data Index: 3096380 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19