Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.7043. Min Act: -0.1700
Data Index: 4431493 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.6106. Min Act: -0.1700
Data Index: 6573228 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.5793. Min Act: -0.1700
Data Index: 22741 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.5168. Min Act: -0.1700
Data Index: 598067 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.5168. Min Act: -0.1700
Data Index: 3489333 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.4543. Min Act: -0.1700
Data Index: 3595363 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.4543. Min Act: -0.1700
Data Index: 323228 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.4543. Min Act: -0.1700
Data Index: 3177042 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.4231. Min Act: -0.1700
Data Index: 2479958 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.4231. Min Act: -0.1700
Data Index: 5779029 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.3918. Min Act: -0.1700
Data Index: 3379154 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.3918. Min Act: -0.1700
Data Index: 8272566 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.3918. Min Act: -0.1700
Data Index: 1130439 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.4231. Min Act: -0.1700
Data Index: 772230 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.3918. Min Act: -0.1700
Data Index: 4003657 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.3918. Min Act: -0.1700
Data Index: 8068295 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.3606. Min Act: -0.1700
Data Index: 8394955 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.3606. Min Act: -0.1700
Data Index: 923671 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.3606. Min Act: -0.1700
Data Index: 1835816 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7043. Min Range: -4.7043
Max Act: 4.3606. Min Act: -0.1700
Data Index: 7754742 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19