Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.7586. Min Act: -0.1700
Data Index: 6939746 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.7274. Min Act: -0.1700
Data Index: 8648180 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6961. Min Act: -0.1700
Data Index: 8648179 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 533182 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 5303198 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 5063898 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6336. Min Act: -0.1700
Data Index: 533177 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.6024. Min Act: -0.1700
Data Index: 8648176 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5711. Min Act: -0.1700
Data Index: 2771111 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5711. Min Act: -0.1700
Data Index: 7347512 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5711. Min Act: -0.1700
Data Index: 6379415 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5711. Min Act: -0.1700
Data Index: 7912663 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5399. Min Act: -0.1700
Data Index: 2521220 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5399. Min Act: -0.1700
Data Index: 3851304 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5399. Min Act: -0.1700
Data Index: 3972586 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5399. Min Act: -0.1700
Data Index: 5689618 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5086. Min Act: -0.1700
Data Index: 6158586 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5086. Min Act: -0.1700
Data Index: 2321984 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5086. Min Act: -0.1700
Data Index: 2640045 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7586. Min Range: -4.7586
Max Act: 4.5086. Min Act: -0.1700
Data Index: 3391061 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19