Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4379 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.5318. Min Act: -0.1700
Data Index: 7055445 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.5006. Min Act: -0.1700
Data Index: 7057413 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.4381. Min Act: -0.1700
Data Index: 6866367 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.4068. Min Act: -0.1700
Data Index: 2823161 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.3443. Min Act: -0.1700
Data Index: 6148384 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.3443. Min Act: -0.1700
Data Index: 3229150 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2818. Min Act: -0.1700
Data Index: 4754369 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2818. Min Act: -0.1700
Data Index: 4226744 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2193. Min Act: -0.1700
Data Index: 3742767 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2818. Min Act: -0.1700
Data Index: 3027435 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2193. Min Act: -0.1700
Data Index: 1390931 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2193. Min Act: -0.1700
Data Index: 3193946 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2193. Min Act: -0.1700
Data Index: 2342566 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2193. Min Act: -0.1700
Data Index: 3428670 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2506. Min Act: -0.1700
Data Index: 213979 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.1881. Min Act: -0.1700
Data Index: 6520283 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.1881. Min Act: -0.1700
Data Index: 6564684 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.1881. Min Act: -0.1700
Data Index: 5344054 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2506. Min Act: -0.1700
Data Index: 6834662 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5318. Min Range: -7.5318
Max Act: 7.2193. Min Act: -0.1700
Data Index: 5651976 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19