Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3814 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.4303. Min Act: -0.1700
Data Index: 1871811 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.3832. Min Act: -0.1700
Data Index: 8282579 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.3989. Min Act: -0.1700
Data Index: 2909070 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.3362. Min Act: -0.1700
Data Index: 2744173 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.3205. Min Act: -0.1700
Data Index: 4416111 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.3048. Min Act: -0.1700
Data Index: 8434219 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.3205. Min Act: -0.1700
Data Index: 7422377 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.2734. Min Act: -0.1700
Data Index: 6139864 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.2577. Min Act: -0.1700
Data Index: 893684 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.2577. Min Act: -0.1700
Data Index: 8102165 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.2420. Min Act: -0.1700
Data Index: 8214894 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.2263. Min Act: -0.1700
Data Index: 7025064 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.2263. Min Act: -0.1700
Data Index: 6672756 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.1791. Min Act: -0.1700
Data Index: 6104600 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.1948. Min Act: -0.1700
Data Index: 6581892 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.1791. Min Act: -0.1700
Data Index: 2376025 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.1633. Min Act: -0.1700
Data Index: 2449611 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.1633. Min Act: -0.1700
Data Index: 8542629 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.1476. Min Act: -0.1700
Data Index: 7423927 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4303. Min Range: -3.4303
Max Act: 3.1319. Min Act: -0.1700
Data Index: 6875000 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19