Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.7769. Min Act: -0.1700
Data Index: 6676386 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.7456. Min Act: -0.1700
Data Index: 849190 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.6519. Min Act: -0.1700
Data Index: 2060047 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.6831. Min Act: -0.1700
Data Index: 1183059 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.6206. Min Act: -0.1700
Data Index: 7477479 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.6206. Min Act: -0.1700
Data Index: 3739058 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.6206. Min Act: -0.1700
Data Index: 8511248 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.5894. Min Act: -0.1700
Data Index: 1382607 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.5894. Min Act: -0.1700
Data Index: 4291303 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.5894. Min Act: -0.1700
Data Index: 7870259 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.5269. Min Act: -0.1700
Data Index: 3202006 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.5269. Min Act: -0.1700
Data Index: 341237 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.5581. Min Act: -0.1700
Data Index: 1356442 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.5269. Min Act: -0.1700
Data Index: 3043280 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.4956. Min Act: -0.1700
Data Index: 3982952 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.4956. Min Act: -0.1700
Data Index: 8026159 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.4956. Min Act: -0.1700
Data Index: 6887791 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.4956. Min Act: -0.1700
Data Index: 320107 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.4644. Min Act: -0.1700
Data Index: 6126871 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7769. Min Range: -4.7769
Max Act: 4.4644. Min Act: -0.1700
Data Index: 4387430 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19