Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.6163. Min Act: -0.1700
Data Index: 8455071 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.4913. Min Act: -0.1700
Data Index: 2810430 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.4601. Min Act: -0.1700
Data Index: 7740282 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.4601. Min Act: -0.1700
Data Index: 483047 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.4288. Min Act: -0.1700
Data Index: 3021068 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.4288. Min Act: -0.1700
Data Index: 1925907 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.3975. Min Act: -0.1700
Data Index: 5329458 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.3975. Min Act: -0.1700
Data Index: 5329457 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.3663. Min Act: -0.1700
Data Index: 5785513 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.3350. Min Act: -0.1700
Data Index: 4972311 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.2725. Min Act: -0.1700
Data Index: 3554367 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.2413. Min Act: -0.1700
Data Index: 4291536 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.2725. Min Act: -0.1700
Data Index: 6421202 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.2413. Min Act: -0.1700
Data Index: 6683234 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.2725. Min Act: -0.1700
Data Index: 489191 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.2725. Min Act: -0.1700
Data Index: 7180455 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.3038. Min Act: -0.1700
Data Index: 8549165 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.2413. Min Act: -0.1700
Data Index: 6515520 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.2413. Min Act: -0.1700
Data Index: 5988150 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6163. Min Range: -4.6163
Max Act: 4.2413. Min Act: -0.1700
Data Index: 5501441 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19