Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 995 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0232. Min Range: -4.0232
Max Act: 4.0232. Min Act: -0.1700
Data Index: 7523627 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.9920. Min Act: -0.1700
Data Index: 4547360 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.9294. Min Act: -0.1700
Data Index: 3276690 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.9294. Min Act: -0.1700
Data Index: 4877882 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8982. Min Act: -0.1700
Data Index: 845730 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8982. Min Act: -0.1700
Data Index: 8775398 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8982. Min Act: -0.1700
Data Index: 4080666 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8669. Min Act: -0.1700
Data Index: 7015652 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8356. Min Act: -0.1700
Data Index: 2283337 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8356. Min Act: -0.1700
Data Index: 836718 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8669. Min Act: -0.1700
Data Index: 2812074 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8356. Min Act: -0.1700
Data Index: 5128450 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8044. Min Act: -0.1700
Data Index: 5629255 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8044. Min Act: -0.1700
Data Index: 5813221 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8044. Min Act: -0.1700
Data Index: 4080665 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8044. Min Act: -0.1700
Data Index: 4815427 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8356. Min Act: -0.1700
Data Index: 6464739 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8044. Min Act: -0.1700
Data Index: 6881866 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.8044. Min Act: -0.1700
Data Index: 3557173 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0232. Min Range: -4.0232
Max Act: 3.7731. Min Act: -0.1700
Data Index: 6445415 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19