Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.5264. Min Act: -0.1700
Data Index: 7994834 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.4638. Min Act: -0.1700
Data Index: 7769117 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.4326. Min Act: -0.1700
Data Index: 5472259 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.3701. Min Act: -0.1700
Data Index: 4504735 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.3701. Min Act: -0.1700
Data Index: 8304184 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.2763. Min Act: -0.1700
Data Index: 4789869 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.2763. Min Act: -0.1700
Data Index: 4856162 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.2763. Min Act: -0.1700
Data Index: 5744632 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.2763. Min Act: -0.1700
Data Index: 5905209 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.2451. Min Act: -0.1700
Data Index: 12602 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.2451. Min Act: -0.1700
Data Index: 6478007 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.2138. Min Act: -0.1700
Data Index: 5746856 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.1826. Min Act: -0.1700
Data Index: 3471260 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.1826. Min Act: -0.1700
Data Index: 3671463 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.1826. Min Act: -0.1700
Data Index: 3025172 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.1826. Min Act: -0.1700
Data Index: 2519146 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.1826. Min Act: -0.1700
Data Index: 1043976 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.2138. Min Act: -0.1700
Data Index: 3386757 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.1826. Min Act: -0.1700
Data Index: 4742725 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5264. Min Range: -4.5264
Max Act: 4.1826. Min Act: -0.1700
Data Index: 1149808 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19